# Account & Billing Source: https://docs.aseed.ai/account/overview Manage your token balance, purchase tokens, and understand how tokens are used for transcription and report generation. ## Overview Aseed uses a token-based billing system. Tokens are consumed when you generate transcripts and reports. You can purchase tokens in packages, earn free tokens through referrals, and monitor your balance throughout your workflow. View your available tokens in the navigation bar. Balance updates automatically after purchases and usage. Buy token packages ranging from 100 to 10,000 tokens with volume discounts for larger packages. Get 200 free tokens for each friend who signs up using your referral link. See estimated token costs before generating transcripts or reports. Actual usage may vary slightly. ## Token balance Your token balance is displayed in the top navigation bar and shows how many tokens you have available. The balance updates automatically: * **After purchases**: When you buy tokens, your balance refreshes immediately * **After usage**: When you generate transcripts or reports, tokens are deducted from your balance * **After referrals**: When someone signs up using your referral link, you receive 200 tokens Your token balance is always visible in the navigation bar, so you can monitor your usage at any time. ## How tokens are used Tokens are consumed when you perform certain actions in Aseed. The system calculates token costs based on several factors: ### Transcription tokens Tokens are charged for generating transcripts from audio or video files. The cost depends on: * **Interview length**: Longer interviews require more tokens * **File type**: Audio and video files are processed differently * **File size**: Larger files may require additional processing Text transcripts uploaded directly don't require transcription tokens since they're already in text format. ### Report generation tokens Tokens are charged for generating analysis reports. The cost depends on: * **Report type**: Each report type (Q\&A, General, Persona, JTBD, Custom) has a base cost * **Number of reports**: The base cost is multiplied by the number of report types you select * **Interview complexity**: More complex interviews may require additional processing You can see the estimated token cost before generating reports. The actual cost may vary slightly based on the complexity of your interview content. ### Batch operations When generating reports for multiple records in a project: * **Transcripts**: Each record that needs transcription is charged separately * **Reports**: Each report type for each record is charged separately * **Total cost**: The system calculates the total tokens needed before you confirm the batch operation Batch generation shows you the total token cost upfront, so you can ensure you have enough tokens before starting. ## Related topics * [Purchase tokens](/account/purchase) * [Referral program](/account/referral) * [Token usage details](/account/usage) # Purchase tokens Source: https://docs.aseed.ai/account/purchase Buy token packages to generate transcripts and reports. ## Overview Purchase tokens in packages to generate transcripts and reports. Token packages range from 100 to 10,000 tokens, with volume discounts available for larger packages. Choose from packages of 100, 500, 1,000, 2,000, 5,000, or 10,000 tokens. Larger packages include discounts, making bulk purchases more cost-effective. Pay in USD, RUB, or KZT depending on your location and payment method. Tokens never expire. Use them anytime, at your own pace. ## How to purchase tokens Click the token balance in the navigation bar, or click **Buy Tokens** when you don't have enough tokens for an operation. Token purchase modal showing package options Token purchase modal showing package options Choose the package size that fits your needs. Larger packages offer better value with volume discounts. The modal shows how many reports you can generate with each package (approximately 1 report per 100 tokens). Selected token package with pricing and discount information Selected token package with pricing and discount information Select your preferred currency from the dropdown. Available currencies depend on your location: * **USD**: Available worldwide via Stripe * **RUB**: Available for Russian users via YooKassa * **KZT**: Available for Kazakh users via Tiptop The system automatically detects your location and suggests the appropriate currency, but you can change it if needed. Click **Proceed to Payment** to complete your purchase. You'll be redirected to the payment provider (Stripe, YooKassa, or Tiptop) to complete the transaction. Payment provider interface for completing token purchase Payment provider interface for completing token purchase After successful payment, your token balance updates automatically. You can start using your tokens immediately. Your balance refreshes automatically after purchase. If it doesn't update, refresh the page or click the balance in the navigation bar. ## Token packages Available token packages and their approximate value: | Package Size | Approximate Reports | Notes | | - | - | - | | **100 tokens** | \~1 report | Good for trying out Aseed | | **500 tokens** | \~5 reports | Small discount available | | **1,000 tokens** | \~10 reports | Popular choice for regular users | | **2,000 tokens** | \~20 reports | Better value with discount | | **5,000 tokens** | \~50 reports | Significant discount | | **10,000 tokens** | \~100 reports | Best value with maximum discount | The number of reports is approximate. Actual usage depends on interview length and the number of report types you generate. ## Payment methods Aseed supports multiple payment providers based on your location and currency: | Currency | Payment Provider | Available Regions | | - | - | - | | **USD** | Stripe | Worldwide | | **RUB** | YooKassa | Russia | | **KZT** | Tiptop | Kazakhstan | Payment processing is handled securely by third-party providers. Aseed never stores your payment information. ## Best practices Larger token packages offer better value with volume discounts. If you plan to use Aseed regularly, consider purchasing larger packages to save on costs. Keep an eye on your token balance in the navigation bar. Purchase tokens before you run out to avoid interruptions in your workflow. Earn free tokens through referrals to supplement your purchased tokens. Share your referral link to get 200 tokens for each friend who signs up. Before generating transcripts or reports, check the estimated token cost. This helps you plan your purchases and avoid unexpected token shortages. ## Related topics * [Account overview](/account/overview) * [Referral program](/account/referral) * [Token usage details](/account/usage) # Referral program Source: https://docs.aseed.ai/account/referral Earn free tokens by inviting friends to Aseed. ## Overview Invite friends to Aseed and earn 200 free tokens for each person who signs up using your referral link. There's no limit to how many tokens you can earn through referrals. The referral program is periodically available. It may not be active at all times. Check the app interface to see if the referral program is currently available. Get 200 free tokens for each friend who signs up using your unique referral link. There's no limit to how many people you can refer or how many tokens you can earn. Copy your referral link and share it via email, messaging, or social media. Tokens are added to your balance automatically when someone signs up. ## Availability The referral program is periodically available and may not be active at all times. When the program is active, you'll see the referral option in your account settings or token balance menu. If you don't see the referral option, the program is currently unavailable. Check back periodically or contact support to inquire about when the referral program will be available again. ## How to use the referral program The referral program must be active to use these features. If you don't see the referral option, the program is currently unavailable. Click the token balance in the navigation bar, then look for the referral option, or access it through your account settings. The referral option is only visible when the program is active. Referral modal showing referral link and copy button Referral modal showing referral link and copy button Click **Copy Link** to copy your unique referral link to your clipboard. The link is automatically generated and unique to your account. Your referral link never expires. You can share it anytime, anywhere. Share your referral link via email, messaging apps, social media, or any communication channel. Include a brief message explaining what Aseed does and why they should try it. Personalize your referral message to increase the likelihood that friends will sign up. Explain how Aseed has helped you with your research. When someone signs up using your referral link, you automatically receive 200 tokens added to your balance. You'll see the balance update in the navigation bar. Tokens are credited immediately when someone completes registration using your referral link. ## How referrals work 1. **You share your link**: Copy and share your unique referral link with friends, colleagues, or anyone interested in Aseed 2. **They sign up**: When someone clicks your link and creates an Aseed account, they're automatically associated with your referral 3. **You get tokens**: 200 tokens are automatically added to your balance 4. **No limits**: There's no limit to how many people you can refer or how many tokens you can earn Referrals are a great way to earn free tokens while helping others discover Aseed. Share your link widely to maximize your token earnings. ## Best practices Share your referral link in communities where people do user research, customer development, or product management. This increases the likelihood of sign-ups from people who will actually use Aseed. When sharing your referral link, briefly explain what Aseed does and how it has helped you. Personal recommendations are more effective than generic links. Monitor your token balance to see when referrals convert. This helps you understand which sharing channels are most effective. Use referral tokens to supplement purchased tokens. This helps you extend your token balance and reduce overall costs. ## Related topics * [Account overview](/account/overview) * [Purchase tokens](/account/purchase) * [Token usage details](/account/usage) # Token usage Source: https://docs.aseed.ai/account/usage Understand how tokens are calculated and charged for transcription and report generation. ## Overview Tokens are consumed when you generate transcripts and reports. The system calculates costs based on interview length, file type, and the number of report types you select. You can see estimated costs before generating, and actual usage may vary slightly. See estimated token costs before generating transcripts or reports. Tokens are only charged when you actually generate transcripts or reports. The estimated cost shown is what you'll be charged. Actual usage may vary slightly based on complexity. For batch operations, see the total cost upfront before confirming. ## How token costs are calculated ### Transcription costs Tokens are charged for generating transcripts from audio or video files. The cost is calculated based on: * **Interview length**: Longer interviews require more tokens * **File duration**: The system processes the entire audio/video file * **File type**: Different file formats may have varying processing requirements Text transcripts uploaded directly don't require transcription tokens since they're already in text format and don't need processing. ### Report generation costs Tokens are charged for generating analysis reports. The cost is calculated based on: * **Base report cost**: Each report type has a base cost * **Number of report types**: The base cost is multiplied by the number of report types you select * **Interview complexity**: More complex interviews with longer transcripts may require additional processing If you select multiple report types (e.g., Q\&A, General, and Persona), the cost is calculated as: base cost × number of report types. ### AI Agent costs Tokens are charged for each assistant message when using the AI Agent to generate Research Context Briefs or Interview Guides. The cost depends on the reasoning mode you choose: * **Fast mode**: 2 tokens per assistant message * Use for quick responses and standard guide/brief generation * Suitable for most use cases * **Thinking mode**: 5 tokens per assistant message * Use for more complex research scenarios requiring deeper analysis * Provides more thorough responses and better handles nuanced requirements You can switch between Fast and Thinking modes at any time during the conversation. Tokens are only charged for assistant messages, not for your questions or input. ### Example calculations **Single record with one report type:** * Transcription: Based on interview length * Q\&A Report: Base report cost * **Total**: Transcription cost + Report cost **Single record with multiple report types:** * Transcription: Based on interview length * Q\&A Report: Base report cost * General Report: Base report cost * Persona Report: Base report cost * **Total**: Transcription cost + (Base report cost × 3) **Batch generation:** * Each record that needs transcription: Individual transcription cost * Each report type for each record: Base report cost × number of types * **Total**: Sum of all transcription and report costs ## Viewing estimated costs ### Before generation Before generating transcripts or reports, you can see the estimated token cost: 1. **Single record**: The token summary shows estimated costs when you select transcript or report options 2. **Batch operations**: The batch generation modal shows total estimated costs for all selected records Token summary showing estimated token cost before generation Token summary showing estimated token cost before generation ### Insufficient tokens If you don't have enough tokens, the system will: 1. **Show required amount**: Display how many tokens you need 2. **Offer to purchase**: Provide a button to buy tokens 3. **Block generation**: Prevent generation until you have enough tokens Token summary showing insufficient tokens warning Token summary showing insufficient tokens warning ## When tokens are charged Tokens are deducted from your balance: * **After successful generation**: Tokens are charged only after transcripts or reports are successfully generated * **Not for failed operations**: If generation fails, tokens are not charged * **Not for viewing**: Viewing existing transcripts or reports doesn't consume tokens * **Not for editing**: Editing transcripts or reports doesn't consume additional tokens Tokens are only charged for successful operations. If something goes wrong during generation, you won't be charged. ## Regeneration costs If you regenerate a transcript or report: * **Full cost applies**: You're charged the same amount as generating it for the first time * **Warning shown**: The system warns you if you're about to regenerate something that already exists * **Consider carefully**: Regenerating typically produces the same result, so consider if it's necessary Regenerating transcripts or reports usually produces identical results. Only regenerate if you've made significant changes to the source material or settings. ## Batch generation costs When generating reports for multiple records: * **Total shown upfront**: The batch generation modal shows the total estimated cost * **Per-record breakdown**: You can see which records will be processed and their individual costs * **All or nothing**: Tokens are charged for all successfully generated items Batch generation modal showing total token cost for multiple records Batch generation modal showing total token cost for multiple records ## Factors affecting token usage Several factors can influence how many tokens are used: | Factor | Impact | Notes | | - | - | - | | **Interview length** | Higher for longer interviews | Longer audio/video files require more processing | | **File type** | Varies by format | Different formats may have different processing requirements | | **Number of report types** | Linear increase | Each additional report type adds to the cost | | **Interview complexity** | Slight variation | More complex content may require additional processing | | **Text transcripts** | No transcription cost | Uploaded text files skip transcription, saving tokens | The estimated cost shown before generation is usually accurate. Actual usage may vary slightly based on content complexity, but the difference is typically minimal. ## Best practices Always review the estimated token cost before generating transcripts or reports. This helps you plan your token usage and avoid unexpected charges. Select only the report types you actually need. Each additional report type increases the cost, so be selective. If you have text transcripts, upload them directly instead of audio/video files. This saves transcription tokens. Regenerating transcripts or reports typically produces the same result. Only regenerate if you've made significant changes or need to update settings. For batch generation, review the total cost before confirming. This helps ensure you have enough tokens for all operations. ## Related topics * [Account overview](/account/overview) * [Purchase tokens](/account/purchase) * [Referral program](/account/referral) * [Create interview guide](/interviews/guide-builder) - Learn about AI Agent token costs for guide generation * [Add research context](/projects/context) - Learn about AI Agent token costs for Research Context Brief generation # Cancel Chat Source: https://docs.aseed.ai/api-reference/agent/cancel-chat /api-reference/openapi-filtered.json post /agent/chat/cancel Cancel an in-progress chat request. Request body: - thread_id: Thread ID Returns: - Cancellation status # Chat Source: https://docs.aseed.ai/api-reference/agent/chat /api-reference/openapi-filtered.json post /agent/chat Send a message to the AI agent and receive a streaming response. Request body: - thread_id: Agent thread ID - message: User message text Returns: - Streaming response chunks # Create Thread Source: https://docs.aseed.ai/api-reference/agent/create-thread /api-reference/openapi-filtered.json post /agent/threads Create a new agent thread. Request body: - name: Optional thread name Returns: - Created thread object # Delete Thread Source: https://docs.aseed.ai/api-reference/agent/delete-thread /api-reference/openapi-filtered.json delete /agent/threads/{thread_id} Soft-delete an agent thread. Path params: - thread_id: Thread ID # Get History Source: https://docs.aseed.ai/api-reference/agent/get-history /api-reference/openapi-filtered.json get /agent/threads/{thread_id}/history Get message history for an agent thread. Path params: - thread_id: Thread ID Returns: - Ordered list of thread messages # Get Thread Source: https://docs.aseed.ai/api-reference/agent/get-thread /api-reference/openapi-filtered.json get /agent/threads/{thread_id} Get an agent thread by ID. Path params: - thread_id: Thread ID Returns: - Thread object # Get Threads Source: https://docs.aseed.ai/api-reference/agent/get-threads /api-reference/openapi-filtered.json get /agent/threads Get all agent threads for the current user. Returns: - List of user threads # Update Thread Source: https://docs.aseed.ai/api-reference/agent/update-thread /api-reference/openapi-filtered.json patch /agent/threads/{thread_id} Update an existing agent thread. Path params: - thread_id: Thread ID Request body: - name: New thread name Returns: - Updated thread object # Health Check Source: https://docs.aseed.ai/api-reference/health-check /api-reference/openapi-filtered.json get /health # Assign Utterance Speaker Source: https://docs.aseed.ai/api-reference/insight/assign-utterance-speaker /api-reference/openapi-filtered.json patch /insight/{rec_id}/transcript_utterance_speaker # Cancel Generation Source: https://docs.aseed.ai/api-reference/insight/cancel-generation /api-reference/openapi-filtered.json post /insight/{rec_id}/cancel-generation/ # Chat Message Source: https://docs.aseed.ai/api-reference/insight/chat-message /api-reference/openapi-filtered.json post /insight/{rec_id}/chat/ # Check Space Source: https://docs.aseed.ai/api-reference/insight/check-space /api-reference/openapi-filtered.json post /insight/check_space/ # Create New Thread Source: https://docs.aseed.ai/api-reference/insight/create-new-thread /api-reference/openapi-filtered.json post /insight/{rec_id}/chat/new-thread/ # Export Report To Docx Source: https://docs.aseed.ai/api-reference/insight/export-report-to-docx /api-reference/openapi-filtered.json post /insight/export/report-docx/{rec_id} Export a specific report from a record to DOCX format. This endpoint fetches a report's Markdown content from the database and converts it to DOCX format. Parameters: - **rec_id**: Record UUID - **report_type**: Type of report (qa, persona, custom, jtbd) - **version**: Optional report version (defaults to latest) - **locale**: Document language - **admonition_support**: Enable admonition blocks Returns: - DOCX file Errors: - 404: Record or report not found - 400: Invalid report type - 500: Conversion failed # Export To Docx Source: https://docs.aseed.ai/api-reference/insight/export-to-docx /api-reference/openapi-filtered.json post /insight/export/docx Convert Markdown file to DOCX format using Pandoc. This endpoint accepts a Markdown file and converts it to Microsoft Word (.docx) format with support for custom admonition blocks (ad-info, ad-warning, ad-tip). Parameters: - **file**: Markdown file (multipart/form-data) - **record_id**: Optional record UUID for logging and tracking - **locale**: Document language (e.g., "ru-RU", "en-US") - **title**: Output filename (without extension) - **admonition_support**: Enable Lua filters for admonition blocks Returns: - DOCX file with proper MIME type and Content-Disposition header Errors: - 400: Invalid file or parameters - 413: File too large (>8 MB) - 500: Conversion failed - 504: Conversion timeout (>60s) # Generate Report Source: https://docs.aseed.ai/api-reference/insight/generate-report /api-reference/openapi-filtered.json post /insight/{rec_id}/generate/ # Get Chat History Source: https://docs.aseed.ai/api-reference/insight/get-chat-history /api-reference/openapi-filtered.json get /insight/{rec_id}/chat/ # Get Chat Threads Source: https://docs.aseed.ai/api-reference/insight/get-chat-threads /api-reference/openapi-filtered.json get /insight/{rec_id}/chat/threads/ # Get Context Tokens Batch Source: https://docs.aseed.ai/api-reference/insight/get-context-tokens-batch /api-reference/openapi-filtered.json get /insight/context-tokens-batch/ Get aggregated context token sum for a list of records. Query parameters: - ids: comma-separated list of record UUIDs - context_type: one of ["transcripts", "qa"] # Get Custom Report Source: https://docs.aseed.ai/api-reference/insight/get-custom-report /api-reference/openapi-filtered.json get /insight/{rec_id}/custom-report # Get Detailed Record Source: https://docs.aseed.ai/api-reference/insight/get-detailed-record /api-reference/openapi-filtered.json get /insight/{rec_id}/ # Get Intro Source: https://docs.aseed.ai/api-reference/insight/get-intro /api-reference/openapi-filtered.json get /insight/intro # Get Jtbd Markdown Report Source: https://docs.aseed.ai/api-reference/insight/get-jtbd-markdown-report /api-reference/openapi-filtered.json get /insight/{rec_id}/jtbd-markdown-report # Get Persona Report Source: https://docs.aseed.ai/api-reference/insight/get-persona-report /api-reference/openapi-filtered.json get /insight/{rec_id}/persona-report # Get Pipeline Status Source: https://docs.aseed.ai/api-reference/insight/get-pipeline-status /api-reference/openapi-filtered.json get /insight/{rec_id}/pipeline-status/ # Get Qa Report Source: https://docs.aseed.ai/api-reference/insight/get-qa-report /api-reference/openapi-filtered.json get /insight/{rec_id}/qa-report # Get Record Meta Source: https://docs.aseed.ai/api-reference/insight/get-record-meta /api-reference/openapi-filtered.json get /insight/{rec_id}/meta Get lightweight metadata for a record. Query parameters: - include: comma-separated list of additional fields to include (e.g., "file_info,processing_stats") # Get Record Tokens Source: https://docs.aseed.ai/api-reference/insight/get-record-tokens /api-reference/openapi-filtered.json get /insight/{rec_id}/tokens Get expected tokens for a record without loading heavy data. This endpoint is optimized for batch token calculation scenarios. Returns only pricing information, not full record data. Performance: ~1-2 seconds (vs 25+ seconds for full detailed record) # Get Records Source: https://docs.aseed.ai/api-reference/insight/get-records /api-reference/openapi-filtered.json get /insight/ # Get Records Meta Batch Source: https://docs.aseed.ai/api-reference/insight/get-records-meta-batch /api-reference/openapi-filtered.json get /insight/meta-batch Get lightweight metadata for multiple records in batch. Query parameters: - ids: comma-separated list of record UUIDs (e.g., "uuid1,uuid2,uuid3") - include: comma-separated list of additional fields to include (e.g., "file_info,processing_stats") # Get Records Paginated Source: https://docs.aseed.ai/api-reference/insight/get-records-paginated /api-reference/openapi-filtered.json get /insight/paginated Get paginated records list. Query parameters: - page: page number (default: 1) - limit: records per page (default: 50, max: 200) - search: case-insensitive search across name, file name, email - status: repeated query param of record statuses - type: repeated query param of logical file types (audio/video/text) - archived: filter by archived flag # Get Shared Custom Report Source: https://docs.aseed.ai/api-reference/insight/get-shared-custom-report /api-reference/openapi-filtered.json get /insight/public/{rec_id}/custom-report Get public/shared Custom report by record ID. # Get Shared Jtbd Markdown Report Source: https://docs.aseed.ai/api-reference/insight/get-shared-jtbd-markdown-report /api-reference/openapi-filtered.json get /insight/public/{rec_id}/jtbd-markdown-report Get public/shared JTBD Markdown report by record ID. # Get Shared Persona Report Source: https://docs.aseed.ai/api-reference/insight/get-shared-persona-report /api-reference/openapi-filtered.json get /insight/public/{rec_id}/persona-report Get public/shared Persona report by record ID. # Get Shared Qa Report Source: https://docs.aseed.ai/api-reference/insight/get-shared-qa-report /api-reference/openapi-filtered.json get /insight/public/{rec_id}/qa-report Get public/shared QA report by record ID. # Refine Transcript Source: https://docs.aseed.ai/api-reference/insight/refine-transcript /api-reference/openapi-filtered.json post /insight/{rec_id}/transcript_refine Refine transcript using LLM to fix diarization errors. Creates a new version with the refined transcript. Returns the new version number. # Regenerate Report Source: https://docs.aseed.ai/api-reference/insight/regenerate-report /api-reference/openapi-filtered.json post /insight/{rec_id}/regenerate/ # Reset Report Status Source: https://docs.aseed.ai/api-reference/insight/reset-report-status /api-reference/openapi-filtered.json post /insight/{rec_id}/reset-status/ # Toggle Speaker Respondent Source: https://docs.aseed.ai/api-reference/insight/toggle-speaker-respondent /api-reference/openapi-filtered.json patch /insight/{rec_id}/speaker_respondent # Update Custom Report Source: https://docs.aseed.ai/api-reference/insight/update-custom-report /api-reference/openapi-filtered.json patch /insight/{rec_id}/custom-report # Update Jtbd Markdown Report Source: https://docs.aseed.ai/api-reference/insight/update-jtbd-markdown-report /api-reference/openapi-filtered.json patch /insight/{rec_id}/jtbd-markdown-report # Update Persona Report Source: https://docs.aseed.ai/api-reference/insight/update-persona-report /api-reference/openapi-filtered.json patch /insight/{rec_id}/persona-report # Update Qa Report Source: https://docs.aseed.ai/api-reference/insight/update-qa-report /api-reference/openapi-filtered.json patch /insight/{rec_id}/qa-report # Update Records Source: https://docs.aseed.ai/api-reference/insight/update-records /api-reference/openapi-filtered.json put /insight/update/ # Update Setup Source: https://docs.aseed.ai/api-reference/insight/update-setup /api-reference/openapi-filtered.json patch /insight/{rec_id}/setup/ Update setup configuration for a record without generating reports. Updates only the fields provided in the request. Updates the latest setup version. Does not trigger report generation or change record status. Parameters: - rec_id: Record UUID - request: UpdateSetupRequest with fields to update (all optional) Returns: - 204 No Content on success # Update Speaker Name Source: https://docs.aseed.ai/api-reference/insight/update-speaker-name /api-reference/openapi-filtered.json patch /insight/{rec_id}/speaker_name # Update Utterance Source: https://docs.aseed.ai/api-reference/insight/update-utterance /api-reference/openapi-filtered.json patch /insight/{rec_id}/transcript_utterance # Upload File Source: https://docs.aseed.ai/api-reference/insight/upload-file /api-reference/openapi-filtered.json post /insight/upload/ # Upload Text File Source: https://docs.aseed.ai/api-reference/insight/upload-text-file /api-reference/openapi-filtered.json post /insight/upload_text/ # Check Space Source: https://docs.aseed.ai/api-reference/insight_public/check-space /api-reference/openapi-filtered.json patch /insight/public/{rec_id}/switch # Get Public Report Source: https://docs.aseed.ai/api-reference/insight_public/get-public-report /api-reference/openapi-filtered.json get /insight/public/{rec_id}/ # Create Rooms Source: https://docs.aseed.ai/api-reference/interviews/create-rooms /api-reference/openapi-filtered.json post /api/interviews/rooms Create interview rooms for a project. Creates one or more interview rooms linked to a project. Each room gets a unique access token for the respondent URL. Parameters: - project_id: UUID of the project (required) - count: Number of rooms to create (default: 1, max: 100) - max_duration_minutes: Maximum interview duration (default: 30) - expires_in_days: Days until room links expire (default: 7) Returns: - List of created rooms with their URLs # Delete Room Source: https://docs.aseed.ai/api-reference/interviews/delete-room /api-reference/openapi-filtered.json delete /api/interviews/rooms/{room_id} Cancel/delete an interview room. Parameters: - room_id: UUID of the room Returns: - Success message # Get Agent Config Source: https://docs.aseed.ai/api-reference/interviews/get-agent-config /api-reference/openapi-filtered.json get /api/interviews/agent-config/{interview_room_id} Get full interview configuration for the agent. This endpoint is used by the LiveKit agent to fetch complete interview configuration (including interview_guide) when only interview_room_id is provided in the token metadata. This avoids HTTP 414 errors from overly long tokens. Parameters: - interview_room_id: UUID of the interview room Headers: - X-Agent-Secret: Optional shared secret for authentication Returns: - Full interview configuration including interview_guide # Get Interview Config Source: https://docs.aseed.ai/api-reference/interviews/get-interview-config /api-reference/openapi-filtered.json get /api/interviews/config Return interview config (e.g. tokens per 30 min) so the client can show correct costs. # Get Room Source: https://docs.aseed.ai/api-reference/interviews/get-room /api-reference/openapi-filtered.json get /api/interviews/rooms/{room_id} Get details of a specific interview room. Parameters: - room_id: UUID of the room Returns: - Room details # Get Room Info Source: https://docs.aseed.ai/api-reference/interviews/get-room-info /api-reference/openapi-filtered.json get /api/interviews/join/{access_token} Get public information about an interview room. This is a public endpoint for respondents to get room info before joining. Does not require authentication. Parameters: - access_token: The unique token from the interview URL Returns: - Room information (name, duration, status) # Get Rooms Source: https://docs.aseed.ai/api-reference/interviews/get-rooms /api-reference/openapi-filtered.json get /api/interviews/rooms Get interview rooms for the current user. Parameters: - project_id: Optional filter by project - status: Optional filter by status (pending, active, completed, expired, cancelled) Returns: - List of interview rooms # Join Room Source: https://docs.aseed.ai/api-reference/interviews/join-room /api-reference/openapi-filtered.json post /api/interviews/join/{access_token} Join an interview room as a respondent. This is a public endpoint. Validates the room, records the respondent email, and returns a LiveKit token for connection. Parameters: - access_token: The unique token from the interview URL - email: Respondent's email address Returns: - LiveKit token and connection details # Participant Leave Source: https://docs.aseed.ai/api-reference/interviews/participant-leave /api-reference/openapi-filtered.json post /api/interviews/join/{access_token}/leave Notify that the respondent has left the interview (e.g. clicked End call). Public endpoint. Marks the room as completed so status updates even when the LiveKit room_finished webhook does not reach the backend (e.g. local dev). # Receive Session Report Source: https://docs.aseed.ai/api-reference/interviews/receive-session-report /api-reference/openapi-filtered.json post /api/interviews/session-report Receive session report from the LiveKit agent. This endpoint is called by the agent when an interview session ends. The report contains the conversation transcript which is parsed and saved in AssemblyAI format. Parameters: - interview_room_id: UUID of the interview room - report: Session report dictionary from the agent Headers: - X-Agent-Secret: Optional shared secret for authentication Returns: - Success message with room and record IDs # Update Room Source: https://docs.aseed.ai/api-reference/interviews/update-room /api-reference/openapi-filtered.json patch /api/interviews/rooms/{room_id} Update an interview room. Only rooms in 'pending' status can be updated. Use this to override project context for a specific interview. Parameters: - room_id: UUID of the room - research_goals_override: Override research goals (null to clear) - interview_guide_override: Override interview guide (null to clear) - max_duration_minutes: New max duration - expires_at: New expiration time Returns: - Updated room details # API Reference Source: https://docs.aseed.ai/api-reference/introduction Public API reference for Aseed Insight ## Welcome This section contains the public API reference for **Aseed Insight**. Endpoints in this tab are generated from the filtered OpenAPI schema used by Mintlify. Schema used for this documentation (admin routes excluded). Raw backend schema with all available routes. ## Base URL Use this base URL for API requests: ``` https://app.aseed.ai/custdev ``` ## API Groups Main endpoint groups in the current schema: * **insight / insight\_public** - records, transcripts, generation, and chat * **projects** - project management * **project\_reports / project\_reports\_public** - project report generation and public access * **prompts** - custom prompt operations * **presets** - preset operations * **agent** - AI assistant and related endpoints * **interviews** - interview rooms and interview flow * **webhooks** - integration webhook endpoints Admin endpoints are intentionally excluded from this tab. ## Authentication This API uses `Bearer` authentication (`HTTPBearer`). Check each endpoint for exact requirements. You can import the OpenAPI schema into Postman or Insomnia for testing and collections generation. # Clone System Preset Source: https://docs.aseed.ai/api-reference/presets/clone-system-preset /api-reference/openapi-filtered.json post /presets/{preset_id}/clone/ Clone a system preset to create a user preset. # Create Preset Source: https://docs.aseed.ai/api-reference/presets/create-preset /api-reference/openapi-filtered.json post /presets/ Create a new preset. # Delete Preset Source: https://docs.aseed.ai/api-reference/presets/delete-preset /api-reference/openapi-filtered.json delete /presets/{preset_id}/ Delete a preset (soft delete). # Get Presets Source: https://docs.aseed.ai/api-reference/presets/get-presets /api-reference/openapi-filtered.json get /presets/ Get all presets for the current user (user presets + system presets). # Get System Presets Source: https://docs.aseed.ai/api-reference/presets/get-system-presets /api-reference/openapi-filtered.json get /presets/system/ Get only system presets. # Update Preset Source: https://docs.aseed.ai/api-reference/presets/update-preset /api-reference/openapi-filtered.json put /presets/{preset_id}/ Update an existing preset. # Create Project Report Source: https://docs.aseed.ai/api-reference/project_reports/create-project-report /api-reference/openapi-filtered.json post /projects/{project_id}/reports # Delete Project Report Source: https://docs.aseed.ai/api-reference/project_reports/delete-project-report /api-reference/openapi-filtered.json delete /projects/{project_id}/reports/{report_id} # Get Project Report Source: https://docs.aseed.ai/api-reference/project_reports/get-project-report /api-reference/openapi-filtered.json get /projects/{project_id}/reports/{report_id} # Get Public Project Report Source: https://docs.aseed.ai/api-reference/project_reports/get-public-project-report /api-reference/openapi-filtered.json get /projects/public/{project_id}/reports/{report_id} Fetch a public project report without authentication. # List Project Reports Source: https://docs.aseed.ai/api-reference/project_reports/list-project-reports /api-reference/openapi-filtered.json get /projects/{project_id}/reports # Update Project Report Source: https://docs.aseed.ai/api-reference/project_reports/update-project-report /api-reference/openapi-filtered.json put /projects/{project_id}/reports/{report_id} # Create Project Source: https://docs.aseed.ai/api-reference/projects/create-project /api-reference/openapi-filtered.json post /projects/create Create a new project. Parameters: - name: Project name (required) - description: Project description (optional) - research_goals: Research goals for the project (optional) - interview_guide: Interview guide for the project (optional) Returns: - ProjectResponse with project details Note: Files should be uploaded separately using the existing upload API and linked to the project via project_id parameter. # Delete Project Source: https://docs.aseed.ai/api-reference/projects/delete-project /api-reference/openapi-filtered.json delete /projects/{project_id} Delete a project (soft delete). Parameters: - project_id: Project UUID Returns: - Success message Note: This will manually unlink all records from the project by setting their project_id to NULL, since ondelete='SET NULL' only works with physical deletion, not soft deletion. # Get Project Details Source: https://docs.aseed.ai/api-reference/projects/get-project-details /api-reference/openapi-filtered.json get /projects/{project_id} Get project details by ID. Parameters: - project_id: Project UUID Returns: - ProjectResponse with project details # Get Project Records Source: https://docs.aseed.ai/api-reference/projects/get-project-records /api-reference/openapi-filtered.json get /projects/{project_id}/records Get all records for a specific project. Parameters: - project_id: Project UUID Returns: - List of records with their details # Get Projects Source: https://docs.aseed.ai/api-reference/projects/get-projects /api-reference/openapi-filtered.json get /projects/ Get all projects for the current user. Returns: - List of ProjectResponse # Update Project Source: https://docs.aseed.ai/api-reference/projects/update-project /api-reference/openapi-filtered.json put /projects/{project_id} Update an existing project. Parameters: - project_id: Project UUID - name: New project name (optional) - description: New description (optional) - status: New status (optional) - research_goals: New research goals (optional) - interview_guide: New interview guide (optional) Returns: - ProjectResponse with updated project details # Create Prompt Source: https://docs.aseed.ai/api-reference/prompts/create-prompt /api-reference/openapi-filtered.json post /prompts/ Create a new prompt. # Delete Prompt Source: https://docs.aseed.ai/api-reference/prompts/delete-prompt /api-reference/openapi-filtered.json delete /prompts/{prompt_id}/ Delete a prompt (soft delete). # Get Prompts Source: https://docs.aseed.ai/api-reference/prompts/get-prompts /api-reference/openapi-filtered.json get /prompts/ Get all prompts for the current user. # Update Prompt Source: https://docs.aseed.ai/api-reference/prompts/update-prompt /api-reference/openapi-filtered.json put /prompts/{prompt_id}/ Update an existing prompt. # Handle Livekit Webhook Source: https://docs.aseed.ai/api-reference/webhooks/handle-livekit-webhook /api-reference/openapi-filtered.json post /api/webhooks/livekit Handle webhooks from LiveKit server. LiveKit sends webhooks for various events: - room_started: When a room is created - room_finished: When a room is closed - participant_joined: When someone joins - participant_left: When someone leaves - egress_started: When recording starts - egress_ended: When recording finishes Security: Webhook signature verification is REQUIRED. The Authorization header must contain a valid JWT signed with LIVEKIT_API_SECRET. See: https://docs.livekit.io/home/server/webhooks/ # Product updates Source: https://docs.aseed.ai/changelog New releases and improvements ## Video-Aware AI Interviews **Gemini 3.8 Live:** AI Interviewer now runs on the stable Gemini 3.8 Live model with native video understanding. **Camera and screen share:** Respondents can turn on the camera and share their screen during the interview. The model sees the video stream live, so you can run full UX tests — ask users to show a product, walk through a flow, or share a bug on screen. **Recorded with video:** Sessions with camera or screen share are saved as video recordings. Learn more: [AI Interviewer](/projects/ai-interviewer) ## Full-Duplex AI Interviews **GPT-Live-1:** AI Interviewer now supports OpenAI's full-duplex realtime model for more natural conversations, including interruptions and turn-taking. ## Interface Polish and Report Readability **UI polish:** Minor interface fixes and pixel-level refinements across the workspace for a cleaner, more consistent look and feel. **Report readability:** Report pages are easier to scan, with clearer hierarchy between body text, headings, and emphasis. ## Manage Your Workspace from Chat **Workspace actions in chat:** Ask the Research Assistant to create or update projects, rename and move records, archive or restore them, reset failed processing, update record setup, and preview or run report generation — without leaving the conversation. **Understands names, not IDs:** Refer to projects and records by name, exactly as you would in conversation. The assistant searches your workspace, finds the right item, and completes the action — including multi-step requests like "show the records in this project, then rename it". **Confirmation for sensitive actions:** Archiving, resetting, and paid report generation show a confirmation card with the expected token cost before anything runs. Generation uses the same Aseed token balance and billing rules as the app. **Live updates:** Completed actions appear as cards in the chat, and your project and record lists refresh automatically. **Responds in your language:** The assistant answers workspace requests in the language you write in. Learn more: [Research Assistant](/projects/context) ## Manage Aseed from Your AI Client **Projects:** Create projects and update their name, description, status, research goals, and interview guide from Cursor, Codex, Claude, ChatGPT, or another compatible MCP client. **Records:** Rename records, move them between projects, archive or restore them, safely reset failed processing, and update goals, guides, meeting notes, custom prompts, participant details, languages, and speech-to-text settings. **Report generation:** List available prompts and presets, preview the exact expected token cost, generate or regenerate single-record reports, create project-report configurations, and run project reports in Fast or Thinking mode. Generation uses the same Aseed token balance and billing rules as the app. **Safe write access:** New connections receive the supported read and write permissions by default. Reversible or paid actions require explicit confirmation, ownership is checked on every operation, and idempotent retries prevent duplicate objects, jobs, and token charges. If you connected Aseed MCP before version 1.5.1, disconnect and reconnect it to review and approve the new write permissions. Existing read-only grants are not expanded automatically. File upload, deletion, transcript editing, token purchase, public-sharing controls, and AI Interviewer room management are not included in this release. Learn more: [Aseed MCP](/sharing/mcp) ## Aseed MCP Server **Connect your AI client:** Link Cursor, Codex, Claude, ChatGPT, or another MCP client to Aseed at `https://app.aseed.ai/mcp`. **Read your workspace:** Search and fetch projects, records, transcripts, reports, AI Interviewer room metadata, and your token balance. Access follows your Aseed account permissions. **Read-only:** The server does not upload, edit, delete, generate reports, start interviews, or spend tokens. You sign in with browser OAuth. Learn more: [Aseed MCP](https://docs.aseed.ai/sharing/mcp) ## AI Interviewer Models and Interview Quality **Models:** The AI interviewer now uses updated models under the hood. **Interview quality:** Live voice interviews should run more smoothly, with more consistent and natural conversation flow. Learn more: [AI Interviewer](/projects/ai-interviewer) ## Stability and Performance Bug fixes, stability improvements, performance enhancements. ## AI Interviewer, UI, and Performance **AI interviewer:** Voice interview flow and agent behavior are tuned for smoother conversations and more consistent responses. **UI:** Small refinements across the app. **Performance:** Client runs faster. ## Transcript Quality Check and Participant Activity Stats **Quality Check panel:** The transcript page now shows a structured quality assessment for interview and transcript quality. You can see deep interview status, overall ratings, transcription quality, diarization quality, issue tags, and concise comments. **Stricter quality scoring:** Quality assessment is now more resistant to malformed transcripts, parsing artifacts, and speaker-label noise. **Participant activity stats:** The transcript metadata panel now shows participant activity metrics, including speaking share, utterance counts, total characters, and interview duration. Learn more: [Transcribe interviews](/interviews/transcribe) ## Navigation and Split View for Reports **Navigation:** You can switch between projects and records from the navbar from almost anywhere in the app. **Split view:** When viewing a project report, you can open a second panel and compare the main project report with single reports in the project side by side. Learn more: [Project reports](/reports/project), [Manage projects](/projects/manage) ## Research Assistant and Ask Project **Ask Project:** You can ask questions about project reports and get answers grounded in project documents with citations. You can also choose specific reports or records and ask questions only about that subset. **Research Assistant:** The sidebar section formerly named "Research Context" is now "Research Assistant" and supports the full Ask Project workflow. Learn more: [Research Assistant](/projects/context) ## More Reliable Under Load **Backend architecture update:** We completed a major internal upgrade across the custdev backend, client, and LiveKit integration. You keep the same API and workflows. **What you get:** Response times and stability under concurrent load are more predictable. Report generation, interview flows, and webhook processing are less likely to degrade during peak usage. **No action required:** No changes to how you use Aseed; everything works as before, with better resilience. ## Transcription Quality Improvements **Speaker labeling:** Transcripts now assign lines to the right speaker much more reliably across all languages. **Speech to text:** Spoken words are now converted to text much more accurately, with the biggest gains for: * Indonesian * Kazakh * Korean * Russian * Thai * Ukrainian * and other languages **Mixed languages in Auto mode:** Multi-language mode now works in Auto mode, so one interview can include two or three languages. Learn more: [Transcribe interviews](/interviews/transcribe) ## AI Interviewer in Projects Run live AI voice interviews from project links and save completed sessions as records. **Project links**: Create links with duration, expiration, voice, language, and optional topics. **Respondent flow**: Participants join via `/interview/[token]` without login, complete onboarding, and start the call. **Rejoin + transcript**: Rejoin works for the same email during active sessions, and transcripts remain available during and after the call. Learn more: [AI Interviewer](/projects/ai-interviewer), [Manage projects](/projects/manage) ## Rich Text and Readability Improvements **Better readability in setup cards**: Context, guide, and notes now display as rich text in project setup and single report setup. **Updated modal UI**: Context/guide/notes modal was redesigned for clearer reading and editing. **Performance improvements**: General performance optimizations across the app. Learn more: [Research Assistant](/projects/context), [Generate single reports](/reports/single) ## Sidebar and Processing Stability Updates **Projects in sidebar**: Sidebar now shows 3 recent projects and supports quick creation via `+`. **Mobile setup UI fixes**: Improved project setup layout and behavior on mobile devices. **More stable parallel report processing**: Backend parallel report processing is now more stable under higher load. Learn more: [Manage projects](/projects/manage), [Create project reports](/reports/project) ## Enhanced Research Assistant Chat Experience **Forced Tool Calls**: Force the Research Assistant to use specific tools by selecting actions before sending your message. Use the `+` button or type `/` to choose from Research Assistant, Interview Guide, or Documentation. The selected action appears as a badge that you can remove. **UX Knowledge Quiz**: Test your UX knowledge with an interactive 10-question quiz. Choose your difficulty level (Junior, Middle, or Senior) and get detailed feedback on your performance. **Collapsible Long Messages**: User messages longer than 500 characters are automatically collapsed with a "Show more" button. Learn more: [Research Assistant](/projects/context), [Create interview guide](/interviews/guide-builder) ## Research Assistant: context briefs Generate research context briefs through an interactive Q\&A session in the Research Assistant. **Features:** * **Interactive Q\&A**: Answer questions about your research project to generate a structured 11-section brief covering metadata, decision framing, product context, goals, hypotheses, participants, method, and analysis * **Two Input Methods**: Answer questions step by step or provide existing research materials upfront * **Save to Projects**: Save generated briefs directly to your projects, download as Markdown, or copy to clipboard * **Fast & Thinking Modes**: Choose between Fast (2 tokens) or Thinking (5 tokens) modes * **Additional Options**: Skip questions, modify existing briefs, and get validation with follow-up questions Learn more: [Research Assistant](/projects/context) # Edit transcripts Source: https://docs.aseed.ai/interviews/edit Review and edit transcript text, speaker names, and timestamps to ensure accuracy before generating reports. ## Overview Clean transcripts lead to better insights and fewer report revisions. Edit transcripts to fix errors, correct speaker names, and improve overall accuracy before generating reports. ## Editing features With the transcript editor, you can: * **Edit text** - Modify utterance text directly * **Change speaker names** - Update speaker identification * **Adjust timestamps** - Correct timing information (if needed) * **Add or remove utterances** - Manage transcript structure * **Real-time preview** - See changes immediately ## How to edit transcripts Navigate to the **Records** page and select a record, or open a record from a project. Open the **Transcript** tab to see the full transcript with all utterances. Record detail page showing Transcript tab with full transcript displayed Record detail page showing Transcript tab with full transcript displayed Scan for: * Misspellings and typos * Incorrect speaker identification * Missing context or unclear phrases * Timing issues Click on any utterance to edit: * Modify the text directly * Change the speaker name * Update timestamps if needed Transcript editor showing an utterance being edited with text, speaker, and timestamp fields Transcript editor showing an utterance being edited with text, speaker, and timestamp fields Changes are saved automatically as you edit. The updated transcript is used for all future reports. ## Editing tips ### Speaker names * Fix speaker names early in the process * Use consistent naming throughout the transcript * Mark interviewer vs. respondent clearly * Correct names improve report quality significantly ### Text corrections * Fix obvious transcription errors * Add missing words or context * Correct grammar if it affects meaning * Preserve the original meaning while improving clarity ### Best practices Fix speaker names before generating reports. Incorrect speaker identification can significantly impact report accuracy. Review transcripts soon after generation while the interview is fresh in your memory. Focus on fixing errors that affect meaning. Minor typos that don't change interpretation can be left as-is. ## Related topics * [Transcribe records](/interviews/transcribe) - Configure transcription settings * [Records page](/interviews/records) - View and manage all records * [Generate single reports](/reports/single) - Create reports from edited transcripts # Create interview guide Source: https://docs.aseed.ai/interviews/guide-builder Use AI to generate structured interview guides tailored to your research goals. ## Overview The Interview Guide Builder uses AI to help you create comprehensive interview guides. The AI agent asks questions about your research goals, target audience, and context, then generates a structured guide with numbered questions organized into logical sections. ## How to create an interview guide Navigate to **Interview Guide** in the sidebar (available to admins) or go to `/space/agent`. Interview Guide Builder page showing the AI chat interface with empty state and suggestion buttons Interview Guide Builder page showing the AI chat interface with empty state and suggestion buttons You can start in two ways: * **Click the suggestion button**: Click **"Create Interview Guide"** button in the empty state * **Type a message**: Type a message asking to create an interview guide (e.g., "Help me create a guide for depth interviews") The AI will start asking questions about your research. You can also ask questions about Aseed features, workflows, and best practices using the **"Ask About Service"** suggestion button. Respond to the AI's questions about: * Research goals (discovery, validation, usability testing, etc.) * Target audience (existing customers, prospects, churned users, etc.) * Context (product, service, or problem you're researching) * Interview format (video call, phone, in-person, async) * Duration (15min, 30min, 45min, 60min) * Additional context or constraints Interview Guide Builder showing AI conversation with questions and user answers, including mode selector and skip button Interview Guide Builder showing AI conversation with questions and user answers, including mode selector and skip button **Tips for answering questions:** * **Choose your reasoning mode**: Use the mode selector in the input area to switch between **Fast** (2 tokens) and **Thinking** (5 tokens) modes. Fast mode is suitable for most cases, while Thinking mode provides deeper analysis for complex scenarios. * **Skip questions if needed**: If you don't know the answer to a question, click the **Skip** button. The AI will ask alternative questions to gather the information it needs. * **Long messages are automatically collapsed**: If your message is longer than 500 characters, it will be collapsed with a "Show more" button. Click to expand and see the full message. After the AI gathers enough information, it will show a summary and ask for confirmation. Review the plan and choose to generate the guide, continue with more questions, or cancel. Interview Guide Builder showing summary and confirmation dialog Interview Guide Builder showing summary and confirmation dialog Once generated, you'll see: 1. **Preview card in chat** - A card showing the first few lines of the guide with a **View** button 2. **Full guide panel** - Click **View** to open the complete guide in a panel on the right side The guide includes: * Research overview and objectives * Numbered questions organized into logical sections * Follow-up questions for deeper exploration * Researcher recommendations * Preparation checklist Interview Guide Builder showing the generated guide preview card and full panel with Save button Interview Guide Builder showing the generated guide preview card and full panel with Save button After generating the guide, the AI may suggest creating a Research Context Brief. This helps structure your research goals and hypotheses. You can accept the suggestion or continue with the guide. Use the **Save** button in the guide panel to: * **Download as Markdown** - Save the guide as a `.md` file with automatic filename formatting * **Copy to clipboard** - Copy the guide text for pasting elsewhere * **Save to project** - Select a project from the dropdown to attach the guide directly to that project's Interview Guide field Save dropdown menu showing Download, Copy options and project list with badges Save dropdown menu showing Download, Copy options and project list with badges When you save the guide to a project, it automatically populates the Interview Guide field in that project's Research Context section. If the project already has a guide, you'll be asked to confirm overwriting it. Projects with existing guides show a **"Has guide"** badge. Projects without guides show **"No guide"** badge. This helps you see which projects already have interview guides. ## How it works The AI agent uses natural language processing to: * Ask contextual questions in your language * Adapt the conversation based on your answers * Determine when enough information has been collected * Generate a structured guide with numbered questions ## Token usage and cost The AI Agent uses tokens for each assistant message. You can choose between two reasoning modes: **Cost:** 2 tokens per assistant message Use Fast mode for quick responses and standard guide generation. This mode provides fast, efficient answers suitable for most use cases. **Cost:** 5 tokens per assistant message Use Thinking mode for more complex research scenarios that require deeper analysis and reasoning. This mode provides more thorough responses and better handles nuanced requirements. **Tips for working with the AI Agent:** * **Switch modes anytime**: You can switch between Fast and Thinking modes at any time during the conversation using the mode selector in the input area. Choose Fast mode for speed and efficiency, or Thinking mode when you need more comprehensive analysis. Tokens are only charged for assistant messages, not for your questions or input. * **Modify generated guides**: You can ask the AI to modify the guide after it's generated. For example, request a shorter version, add specific topics, or change the style. **Example:** If the AI asks 10 questions and you answer each one, that's 10 assistant responses. In Fast mode, this costs 20 tokens (10 × 2). In Thinking mode, this costs 50 tokens (10 × 5). Your questions don't cost tokens. For more details about token usage and costs, see [Token usage](/account/usage). ## Best practices Be specific about your research goals. The more context you provide, the better the guide will be tailored to your needs. If you don't know the answer to a question, click the **Skip** button on the question card. The AI will ask alternative questions to gather the information it needs. Skipping is useful when: * You haven't decided on a particular aspect yet * The question doesn't apply to your research * You want to provide that information later Select **Fast** mode (2 tokens) for quick responses and standard guide generation. Use **Thinking** mode (5 tokens) when you need deeper analysis for complex research scenarios. You can switch modes at any time during the conversation using the mode selector in the input area. If you have existing research materials, documentation, or notes, you can provide them in your first message. The AI will analyze the materials and extract information, asking only follow-up questions about missing or unclear details. This can save time compared to answering questions one by one. After generating a guide, use the **Save** button in the guide panel to save it directly to a project. This automatically populates the Interview Guide field in that project's Research Context section, eliminating the need to copy and paste manually. You can ask the AI to modify the guide after it's generated. For example: * "Make the guide shorter" * "Add questions about pricing" * "Focus more on user pain points" * "Change the style to be more conversational" The AI will update the guide based on your requirements. Generated guides follow a structured format: * **Introduction Section**: Research overview and objectives * **Question Blocks**: Organized into logical subsections (e.g., Opening, Main Questions, Follow-up, Closing) * **Researcher Recommendations**: Tips and things to watch for * **Preparation Checklist**: What to prepare before interviews Questions are numbered and include optional follow-up questions for deeper exploration. ## Force specific tool calls You can force the AI Agent to use a specific tool for your request. This ensures your message is processed with the right context and capabilities. You can select an action in two ways: **Option 1: Use the action button** * Click the **`+`** button in the input toolbar * Select an action from the dropdown menu: * **Research Context**: Force the AI to create research briefs * **Interview Guide**: Force the AI to generate interview guides * **Documentation**: Force the AI to answer questions about Aseed service **Option 2: Use slash commands** * Type **`/`** in the message input * A menu appears with the same action options * Select an action to apply it to your message The selected action appears as a badge next to the input. You can remove it by clicking the badge. Type your message and send it. The AI will process your request using the selected tool, ensuring the response is tailored to that specific function. Forcing the Interview Guide tool is especially useful when you want to ensure your guide request is processed with the guide generation capabilities, even if the AI might interpret your message differently. When an action is selected, messages are marked with a badge indicating which tool is being used (e.g., "Context Builder", "Guide Builder", "Documentation"). ## Ask questions about Aseed The AI Agent can answer questions about Aseed features, workflows, and best practices. Click **"Ask About Service"** in the empty state or ask questions like: * "How do I create a project?" * "What report types does Aseed support?" * "How does batch generation work?" * "What is the difference between Q\&A and General reports?" You can also force documentation mode by selecting the **Documentation** action before asking your question. This ensures the AI uses the documentation tool to provide accurate, up-to-date answers. Messages with documentation answers are marked with a **"Documentation"** tag to indicate they're based on Aseed documentation. ## Related topics * [Add research context](/projects/context) - Use your generated guide in project context or generate Research Context Brief with AI * [Records page](/interviews/records) - Upload and manage interview records * [Transcribe records](/interviews/transcribe) - Create transcripts from recorded interviews * [Token usage](/account/usage) - Learn about token costs and usage # Records page Source: https://docs.aseed.ai/interviews/records View, search, filter, and manage all your interview records in one place. ## Overview The Records page displays all your interview records in a sortable, filterable table. You can view record details, search and filter records, manage them individually or in bulk, and organize them by projects. ## Records table The records table shows all your interviews with the following information: Records page showing the main records table with columns and data Records page showing the main records table with columns and data | Column | Description | | - | - | | **Title** | Record name (clickable link to record details) | | **Project** | Associated project (clickable link to project) | | **Reports** | Number of generated reports for this record | | **Participants** | Number of interview participants | | **Version** | Record version number | | **Status** | Current processing status (Uploaded, Processing, Finished, Error) | | **Public** | Public link availability indicator | | **Type** | Record type: audio, video, or text | | **Duration** | Interview duration (for audio/video records) | | **Size** | File size in MB | | **Created At** | Record creation date and time | | **Updated At** | Last modification date and time | | **Archived** | Archive status indicator | | **Actions** | Quick actions menu (rename, archive, delete, assign to project) | ### Table features * **Search**: Use the search bar to find records by name * **Filtering**: Click column headers to filter by status, type, project, or other attributes * **Sorting**: Click column headers to sort records * **Column visibility**: Show or hide columns using the column visibility menu * **Bulk actions**: Select multiple records to archive or delete them together * **Pagination**: Table loads more records automatically as you scroll ## Managing records ### Bulk actions Select multiple records using checkboxes in the first column of the table. Records table showing multiple records selected with checkboxes Records table showing multiple records selected with checkboxes Use **Archive** or **Delete** buttons in the toolbar that appears when records are selected. Confirm the action in the confirmation dialog that appears. ### Individual actions Click the **Actions** menu (three dots) on any record to: * **Rename** the record * **Archive** or **Unarchive** the record * **Delete** the record * **Assign to Project** or **Remove from Project** * **Copy Public Link** (if record is public) * **Change Status** (admin only) Records table showing actions menu dropdown for a record Records table showing actions menu dropdown for a record ### Filtering and searching * **Search**: Type in the search bar to find records by name * **Status filter**: Click Status column header to filter by processing status * **Type filter**: Click Type column header to filter by audio/video/text * **Project filter**: Click Project column header to filter by project * **User filter**: Admins can filter by user (Email column) Records table showing search bar and filter options Records table showing search bar and filter options ## Related topics * [Upload records](/interviews/upload) - Upload audio, video, or text files * [Upload text transcripts](/interviews/text-transcripts) - Upload and parse text transcripts * [Transcribe records](/interviews/transcribe) - Configure transcription settings * [Edit transcripts](/interviews/edit) - Review and correct transcripts * [Create interview guide](/interviews/guide-builder) - Generate interview guides with AI * [Manage projects](/projects/manage) - Organize records in projects # Upload text transcripts Source: https://docs.aseed.ai/interviews/text-transcripts Upload pre-written transcripts as text files and select the right parser for your format. ## Overview You can upload pre-written transcripts as text files. This is useful when you have transcripts from other tools or want to import existing transcripts. The system supports multiple text formats and provides parsers to extract speaker names, timestamps, and text from your transcript. ## Supported text formats * **.txt** - Plain text files * **.md** - Markdown files * **.srt** - Subtitle files * **.vtt** - WebVTT subtitle files ## Text transcript parsers When uploading a text file, you need to select a parser that matches your transcript format. The system supports 6 different parsers, each designed for specific transcript formats. ### Choosing the right parser The parser extracts speaker names, timestamps, and text from your transcript. Select the parser that matches your source format: | Parser | Best for | Key features | | - | - | - | | **Speaker Text** | Google Meet, Otter.ai, Trint, Tactiq | No timestamps, speaker names optional | | **Tab-Separated** | Zoom .txt export, Kontur Talk | Timestamps and speakers separated by tabs | | **Plain Text** | Freeform transcripts | Simple line breaks, no structure | | **Subtitles** | Zoom, YouTube, MS Teams, .srt, .vtt | Numbered blocks with time ranges | | **Aseed** | Aseed exported transcripts | Aseed markdown format | | **Datetime** | Custom datetime formats | Full date-time timestamps | ### Parser examples Compare parser formats side-by-side: ```text Speaker Text theme={null} Alice: Hello Bob! Are you ready for the meeting? Bob: Yes, Alice. I have prepared the report. ``` ```text Tab-Separated theme={null} 00:00:02 Alice Hello Bob! Are you ready for the meeting? 00:00:07 Bob Yes, Alice. I have prepared the report. ``` ```text Plain Text theme={null} Hello Bob! Are you ready for the meeting? Yes, Alice. I have prepared the report. ``` ```text Subtitles theme={null} 1 00:00:02,000 --> 00:00:05,000 Alice: Hello Bob! Are you ready for the meeting? 2 00:00:05,000 --> 00:00:09,000 Bob: Yes, Alice. I have prepared the report. ``` ```markdown Aseed theme={null} ### Transcript `1` **Alice (Interviewer):** Hello Bob! Are you ready for the meeting? `2` **Bob:** Yes, Alice. I have prepared the report. ``` ```text Datetime theme={null} <2025-12-19 09:32:43> Alice: Hello Bob! Are you ready for the meeting? <2025-12-19 09:32:45> Bob: Yes, Alice. I have prepared the report. ``` ### Parser details **Speaker Text** — Extracts speaker names from text before colons. Calculates timestamps based on word count. Best for Google Meet, Otter.ai, Trint, Tactiq. **Tab-Separated** — Parses timestamps (HH:MM:SS) and speaker names from tab-separated values. Uses provided timestamps or calculates from sequence. Best for Zoom .txt export, Kontur Talk. **Plain Text** — Treats each non-empty line as a separate utterance. Assigns "Unknown" as speaker. Calculates timestamps from word count. Best for freeform transcripts from other sources. **Subtitles** — Extracts timestamps from subtitle time ranges (HH:MM:SS,mmm --> HH:MM:SS,mmm). Optionally extracts speaker names if present in text. Best for Zoom, YouTube, MS Teams, .srt, .vtt files. **Aseed** — Parses Aseed markdown format with utterance numbers in backticks and speaker names in bold. Calculates timestamps from word count. Best for transcripts exported from Aseed interviews. **Datetime** — Extracts full datetime timestamps and converts them to relative times. Uses time differences between entries for accurate duration calculation. Best for custom formats with full datetime timestamps. ## How to upload text transcripts Click **Upload Files** button on the Records page. Select a text file (.txt, .md, .srt, or .vtt) from your computer. The **Text File Upload** modal opens automatically. Text File Upload modal showing record name field, parser selection, and preview Text File Upload modal showing record name field, parser selection, and preview Enter a **Record Name** for your transcript in the input field. **Select Parser** that matches your transcript format from the dropdown menu. See parser examples above to choose the right one. If you're unsure which parser to use, try different parsers and check the preview to see which one correctly extracts speakers and timestamps. Review the **Preview** section to see how your transcript will be parsed. The preview shows the first 30 lines with speaker names, timestamps, and utterance numbers. Switch to **Edit Text** mode if you need to make manual adjustments to the transcript before uploading. Check validation messages: * Duration should be between 5 minutes and 2.5 hours * Utterances should be between 5 and 1000 * Content must contain detectable utterances Click **Upload Transcript** when ready. The transcript will be processed and added to your records. ## Validation rules The system validates your transcript before upload: * **Duration**: Must be between 5 minutes and 2.5 hours * **Utterances**: Must be between 5 and 1000 utterances * **Content**: Must contain detectable utterances based on selected parser If validation fails, you'll see an error message. Try: * Selecting a different parser * Adjusting the transcript format * Checking for formatting issues ## Preview mode The preview shows how your transcript will look after import: * Speaker names are extracted automatically * Utterances are numbered * Timestamps are calculated (if not present in source) * First 30 lines are shown for performance Switch to **Edit Text** mode to make manual adjustments before uploading. ## Best practices Match your parser to the source format. Using the wrong parser can result in incorrect speaker identification or missing timestamps. Review the preview carefully before uploading. This helps catch formatting issues early. If your transcript doesn't match any parser format exactly, try the Plain Text parser or use Edit Text mode to adjust the format manually. For transcripts with timestamps, use Tab-Separated or Subtitles parsers to preserve timing information. ## Related topics * [Records page](/interviews/records) - View and manage all records * [Upload records](/interviews/upload) - Upload audio, video, or text files * [Transcribe records](/interviews/transcribe) - Configure transcription settings * [Edit transcripts](/interviews/edit) - Review and correct transcripts after upload # Transcribe records Source: https://docs.aseed.ai/interviews/transcribe Configure transcription settings including language, participants, and speaker names to generate accurate transcripts. ## Overview Transcripts are the foundation for all reports. Configure transcription settings before generating transcripts to ensure accuracy and proper speaker identification. ## Transcription settings Before starting transcription, configure these settings in the **Setup** tab of your record: ### Transcript language Select the language of your interview to improve transcription accuracy. The system supports: * **Auto detection** - Automatically detects the language * **Main languages**: English, Russian, Kazakh, Uzbek, Turkmen, Ukrainian, German, French, Spanish, Indonesian * **Other languages**: 50+ additional languages including Chinese, Japanese, Korean, Arabic, and more Selecting the correct language significantly improves transcription accuracy, especially for non-English languages. In **Auto detection**, multi-language mode is enabled by default. One interview can include two or more languages, and transcription will continue without manual switching. ### Number of participants Specify the number of participants in your interview: * **Automatic detection** - Let the system detect participants automatically * **Manual selection** - Choose from 1 to 12 participants ### Participant names Add known participant names to help the system identify speakers: 1. Enter participant names in the **Participant Name** fields 2. Add multiple participants using the **Add Participant** button 3. Remove participants by clicking the X button next to their name Providing participant names helps the system correctly identify speakers throughout the transcript, making reports more accurate. ## How to transcribe records Navigate to a record and open the **Setup** tab. Record detail page showing Setup tab with transcription settings Record detail page showing Setup tab with transcription settings Toggle the **Activate** switch in the Transcript section to enable transcription. Setup tab showing activated transcription with language, participants, and names configured Setup tab showing activated transcription with language, participants, and names configured Select the transcript language from the dropdown menu. Choose from Auto detection or specific languages. Choose the number of participants (1-12) or leave it on automatic detection. Enter known participant names in the **Participant Name** fields to improve speaker identification. Click **Add Participant** to add more names. The system automatically starts transcription when settings are configured. Wait for processing to complete. You can monitor progress in the Status column. ## Best practices If respondents switch between languages in one interview, keep language on **Auto detection**. Fix speaker names early in the process. Correct speaker identification improves report quality. For interviews with multiple speakers, specify the exact number of participants to help the system distinguish between them. ## Related topics * [Records page](/interviews/records) - View and manage all records * [Edit transcripts](/interviews/edit) - Review and correct transcripts after generation # Upload records Source: https://docs.aseed.ai/interviews/upload Upload audio, video, or text files to create new interview records. ## Overview Upload interview recordings or text transcripts to create new records. After upload, you can transcribe media files and generate reports. **Audio**: MP3, WAV, M4A, FLAC, OGG, and other common audio formats\ **Video**: MP4, MOV, AVI, MKV, and other common video formats\ **Text**: TXT, MD, SRT, VTT (for text transcripts) **Minimum**: 1MB for media files, 1KB for text files\ **Maximum**: 5GB per file ## How to upload records Navigate to **Records** in the sidebar to view all your records. Click **Upload Files** in the top-right corner of the Records page. Records page showing Upload Files button in the top-right corner Records page showing Upload Files button in the top-right corner Select one or multiple files from your computer. Files start uploading immediately. You can see upload progress in the Status column of the records table. Records table showing file upload progress indicators Records table showing file upload progress indicators Once uploaded, files are automatically processed for transcription. The status will change from "Uploaded" to "Processing" to "Finished". ## Upload behavior Files upload asynchronously so you can continue working. Real-time upload progress shown for each file. Retry failed uploads from the records table. Files are automatically linked to the project if uploaded from a project page. ## Best practices Use clear file names that help you identify respondents later, for example: "Interview\_John\_Doe\_2024-01-15.mp4" You can upload multiple files at once. The system will process them sequentially. For text files, ensure they're properly formatted transcripts or notes that Aseed can process. See [Upload text transcripts](/interviews/text-transcripts) for detailed information about text file formats and parsers. ## Related topics * [Records page](/interviews/records) - View and manage all records * [Upload text transcripts](/interviews/text-transcripts) - Upload and parse text transcripts with detailed parser information * [Upload records to project](/projects/upload-records) - Upload files directly to a project * [Transcribe interviews](/interviews/transcribe) - Configure transcription settings * [Generate single reports](/reports/single) - Create reports from uploaded records # Overview Source: https://docs.aseed.ai/overview Navigate the Aseed documentation and find the right guide for your task. ## Welcome to Aseed Documentation Use this overview to find the right guide for your task in Aseed. ## Documentation structure Aseed documentation is organized into sections that follow the research workflow: See the full workflow from project setup to report sharing. **When to use:** Learning the full process and step-by-step flow. Create and manage research projects. Each project holds interviews, context, and reports. **When to use:** Creating projects, managing settings, uploading files, running batch operations, and using the Research Assistant. **Key topics:** [Create a project](/projects/create), [Research Assistant](/projects/context), [AI Interviewer](/projects/ai-interviewer), [Manage projects](/projects/manage), [Upload records](/projects/upload-records), [Batch generation](/projects/batch-generation). View, manage, and upload interview records. **When to use:** Uploading interview files, viewing all records, transcribing audio/video, editing transcripts, creating interview guides, uploading text transcripts. **Key topics:** [Records page](/interviews/records), [Upload records](/interviews/upload), [Upload text transcripts](/interviews/text-transcripts), [Transcribe records](/interviews/transcribe), [Edit transcripts](/interviews/edit), [Create interview guide](/interviews/guide-builder). Generate per-interview reports from individual transcripts. **When to use:** Generating reports for individual interviews, understanding different report types, editing and regenerating reports. **Key topics:** [Generate single reports](/reports/single), [Edit reports](/reports/edit), [Report types](/reports/report-types). Compare report types, structure, and use cases. **When to use:** Choosing the right report type, understanding report structures, learning about methodologies. **Key topics:** [Overview](/reports/report-types), [Transcript Report](/reports/report-types/transcript), [Q\&A Report](/reports/report-types/qa), [General Report](/reports/report-types/general), [JTBD Report](/reports/report-types/jtbd), [Persona Report](/reports/report-types/persona), [Custom Report](/reports/report-types/custom). Build aggregated reports across multiple interviews. **When to use:** Creating aggregated reports, using presets, building custom report structures, synthesizing insights across multiple interviews. **Key topics:** [Create a project report](/reports/project), [Use presets](/reports/presets), [Build custom reports](/reports/custom). Share reports with stakeholders through public links or exports. **When to use:** Sharing reports with stakeholders, exporting reports, creating public links, downloading reports. **Key topics:** [Share publicly](/sharing/public), [Export reports](/sharing/export). ## Quick navigation by task | Task | Guide | | - | - | | **Create my first project** | [Workflow](/workflow) → [Create a project](/projects/create) | | **Upload interview files** | [Upload records](/interviews/upload) or [Upload to project](/projects/upload-records) | | **Transcribe audio/video** | [Transcribe records](/interviews/transcribe) | | **Upload text transcripts** | [Upload text transcripts](/interviews/text-transcripts) | | **Generate a report** | [Generate single reports](/reports/single) or [Create a project report](/reports/project) | | **Choose a report type** | [Report types](/reports/report-types) | | **Edit a report** | [Edit reports](/reports/edit) | | **Share a report** | [Share publicly](/sharing/public) or [Export reports](/sharing/export) | | **Create an interview guide** | [Create interview guide](/interviews/guide-builder) - Use AI to generate structured guides | | **Add research context** | [Add research context](/projects/context) - Generate with AI or add manually | | **Run voice AI interviews** | [AI Interviewer](/projects/ai-interviewer) - Create links and collect respondent sessions | | **Manage multiple projects** | [Manage projects](/projects/manage) | | **Process multiple records** | [Batch generation](/projects/batch-generation) | ## Common workflows ### First-time user workflow 1. [Workflow](/workflow) - Understand the workflow 2. [Create a project](/projects/create) - Set up your first project 3. [Fill research context](/projects/context) - Define research goals and objectives (use AI to generate Research Context Brief or add manually) 4. [Upload records](/interviews/upload) - Add interview files 5. [Upload text transcripts](/interviews/text-transcripts) or [Transcribe records](/interviews/transcribe) - Add transcripts or generate from audio/video 6. [Create interview guide](/interviews/guide-builder) - Prepare interview structure 7. [Run AI interviews](/projects/ai-interviewer) - Create links and collect live interviews 8. [Edit transcripts](/interviews/edit) - Review and correct if needed 9. [Generate single reports](/reports/single) - Create your first report 10. [Share or export](/sharing/public) - Share with stakeholders ### Advanced research workflow 1. [Create a project](/projects/create) - Set up your research project 2. [Fill research context](/projects/context) - Define research goals and objectives (use AI to generate Research Context Brief or add manually) 3. [Upload records](/projects/upload-records) - Add interview files to project 4. [Upload text transcripts](/interviews/text-transcripts) or [Transcribe interviews](/interviews/transcribe) - Add transcripts or generate from audio/video 5. [Create interview guide](/interviews/guide-builder) - Generate structured guides with AI and save to project 6. [Run AI interviews](/projects/ai-interviewer) - Launch interview links and collect respondent sessions 7. [Edit transcripts](/interviews/edit) - Review and correct if needed 8. [Batch generation](/projects/batch-generation) - Process multiple records at once 9. [Create a project report](/reports/project) - Synthesize insights across interviews 10. [Share or export](/sharing/public) - Share aggregated findings ### Text transcript workflow 1. [Create a project](/projects/create) - Set up your research project 2. [Fill research context](/projects/context) - Define research goals and objectives 3. [Upload text transcripts](/interviews/text-transcripts) - Upload and parse text files 4. [Create interview guide](/interviews/guide-builder) - Prepare interview structure 5. [Edit transcripts](/interviews/edit) - Review and correct if needed 6. [Generate single reports](/reports/single) - Create reports from transcripts 7. [Create a project report](/reports/project) - Aggregate insights ## Related topics * [What is Aseed](/what-is-aseed) - Understand how Aseed differs from general AI assistants * [Quick Start](/quickstart) - Get your first project report in minutes * [API Reference](/api-reference/introduction) - Developer documentation and API endpoints # AI Interviewer Source: https://docs.aseed.ai/projects/ai-interviewer Create interview links, run voice AI interviews, and store completed sessions in your project. ## Overview AI Interviewer runs live voice interviews through unique links. You create links in a project, share them with respondents, and each completed session is saved as a project record. Open any project and use the **AI Interviewer** section. A respondent speaks with AI in real time. The completed session is saved as a record for transcripts and reports. ## Before you start To create and use interview links, fill both **Research Goals** and **Interview Guide** in the project context first. You should also have enough tokens available for the links you create. Link creation reserves tokens based on link count and duration. ## Create interview links Go to a project, then scroll to the **AI Interviewer** section. Project page showing AI Interviewer section and Create Links button Project page showing AI Interviewer section and Create Links button Click **Create Links**. If context is missing, the button is disabled until you add Research Goals and Interview Guide. In the create modal, set: * Number of links * Interview duration (minutes) * Link expiration (days) * Voice * Language (`Auto`, `Russian`, `English`) * Optional interview topics shown to respondents in onboarding Create Interview Links modal showing duration, expiration, voice, language, and interview topics Create Interview Links modal showing duration, expiration, voice, language, and interview topics Review token reservation, then click **Create Links**. If balance is insufficient, you will see **Buy Tokens**. Use row actions to copy or open each link. Each link is single-use for one respondent interview. ## Manage interview links After creation, links appear in three tabs: * **Active**: pending and in-progress links * **Completed**: finished interviews * **Archived**: cancelled or expired links AI Interviewer links list with Active, Completed, and Archived tabs AI Interviewer links list with Active, Completed, and Archived tabs ### Link statuses | Status | Meaning | | - | - | | `pending` | Link is created but interview has not started. | | `active` | Respondent is currently in session. | | `completed` | Interview is finished and saved. | | `expired` | Link validity period ended. | | `cancelled` | Link was cancelled manually. | ### Row actions Depending on status, you can: * **Copy link** * **Open link** * **Rename** (pending links) * **Edit Context** (pending links) * **Cancel** (pending links) ## What respondents see Respondents open `/interview/[token]` without login, enter email, and join the voice interview. The page includes onboarding cards, microphone permission flow, call controls, and a countdown timer. Key behavior: * Rejoin is supported for the same email while the interview is still active. * If the call ends from timer or explicit leave, the session is marked complete. * The transcript panel is available during and after the call. Public interview page with onboarding card and Start interview button Public interview page with onboarding card and Start interview button ## After interview completion When a session completes, Aseed stores it in the project as a record. You can then: * Open transcript and review interview content * Generate single reports for this record * Include the record in project reports AI Interviewer works best with specific Research Goals and Interview Guide content. Strong context improves both interview quality and report relevance. ## Token behavior * Tokens are reserved when you create links. * Reservation size depends on link count and duration. * Final charging happens when interviews move to **completed**. * Cancelled or expired links do not consume completed-session charges. ## Related topics * [Add research context](/projects/context) * [Manage projects](/projects/manage) * [Upload records](/projects/upload-records) * [Manage records](/projects/manage-records) * [Generate single reports](/reports/single) * [Create project reports](/reports/project) # Batch generation Source: https://docs.aseed.ai/projects/batch-generation Generate multiple reports for multiple records at once to save time. ## Overview Batch generation lets you create reports for multiple records simultaneously. You can generate transcripts and various report types (Q\&A, General, JTBD, Persona, Custom) for all selected records in one operation, saving significant time compared to generating reports individually. ## How to generate reports in batch Navigate to the project containing the records you want to process. Scroll to the bottom of the Project Records section. Click the **Generate Reports** button (or the progress indicator if generation is already in progress). Project Records section showing Generate Reports button at the bottom Project Records section showing Generate Reports button at the bottom In the batch generation modal, choose which report types to generate. See [Report types](/reports/report-types) for detailed information about each type: Batch generation modal showing report type selection and configuration options Batch generation modal showing report type selection and configuration options * **Transcript**: Always selected (required for other reports) * **Q\&A**: Question and answer format * **General**: General insights report * **JTBD**: Jobs-to-be-Done analysis * **Persona**: Persona development report * **Custom**: Custom report with your own prompt Set language options: * **Transcript Language**: Auto-detect or select a specific language * **Report Language**: Same as transcript, or choose a different language If you selected Custom reports, enter your custom prompt that defines what the report should analyze. Toggle **Regenerate existing reports** if you want to overwrite reports that already exist for these records. Check the estimated token cost before generating. If you don't have enough tokens, you'll be prompted to purchase more. Click **Generate** to start batch processing. The modal closes, and you'll see progress indicators on each record. * Each record shows a status badge: "Uploaded", "In Progress", or "Finished" * Records with "In Progress" status show a shimmer animation * You can cancel generation for records that are currently processing * Hover over the Generate Reports button to see a cancel option when generation is active * Hover over the **Generate Reports** button at the bottom of the page * If generation is in progress, a cancel option appears * Click to cancel generation for all in-progress records * Cancellation may take a moment to process ## Configuration options ### Report types * **Transcript**: Converts audio/video to text (always first) * **Q\&A**: Extracts questions and answers * **General**: General insights and observations * **JTBD**: Jobs-to-be-Done analysis * **Persona**: Persona characteristics * **Custom**: Tailored report with your prompt ### Language options * **Auto-detect**: Automatically detects language * **Specific language**: Choose from supported languages * **Report language**: Can differ from transcript language ### Token management * Cost calculated before generation * Tokens consumed when generation starts * Purchase more if needed ## Best practices Start with Transcript and Q\&A reports for most records, then add other types as needed. This balances cost with value. Use batch generation when you have multiple records ready to process. It's more efficient than generating reports one by one. Review your project's Research Goals and Interview Guide before batch generation—they're automatically included in the context for better results. Monitor token balance before large batch operations. Consider processing in smaller batches if token costs are high. Use "Regenerate existing reports" carefully—it will overwrite existing reports and consume tokens again. ## Related topics * [Report types](/reports/report-types) - Understand what each report type contains * [Upload records](/projects/upload-records) * [Manage records](/projects/manage-records) * [Generate single reports](/reports/single) * [Add research context](/projects/context) # Research Assistant Source: https://docs.aseed.ai/projects/context Use the Research Assistant to generate research context, interview guides, ask questions about project reports with citations, manage projects and records from chat, and get help on Aseed. ## Overview The **Research Assistant** is the AI-powered section in the sidebar (link **Research Assistant** or path `/space/agent`). It helps you prepare and use research context, interview guides, and project documents in one place. **What you can do:** Generate a structured Research Context Brief through an interactive Q\&A. The brief defines goals, hypotheses, and method. Save it to a project's Research Goals. Create or refine interview guides with the AI. Save guides directly to a project or use them in the Interview Guide Builder. Ask questions about your project reports. Get answers grounded in project documents with citations. Optionally scope to the whole project or to specific reports and records. Ask questions about Aseed features, workflows, and best practices. Answers are based on up-to-date documentation. Create and update projects, rename and organize records, and preview or run report generation — all from chat, referring to items by name. Research context (goals and interview guide) tells Aseed what you want to learn and how interviews should run. You can add it in two ways: * **AI Generation**: Use the Research Assistant to generate a Research Context Brief through an interactive Q\&A session * **Manual Entry**: Write or paste research goals and interview guide in the project (Research Goals and Interview Guide cards) ## Ask Project Ask Project lets you ask questions about your project's reports and get answers that cite the actual project documents. **How it works:** 1. **Turn on Ask Project** — Click the **Ask Project** suggestion in the empty state or use the **`+`** button and choose **Ask Project**. Select one or more projects. The first time you use a project, Aseed indexes its documents (project report, single reports, transcripts); indexing may take a short time. 2. **Ask a question** — Type your question in the chat. The assistant searches the selected project's documents and returns an answer with **citations** to the source report or record. 3. **Scope to specific documents (optional)** — By default, answers use all indexed documents in the selected project(s). You can narrow the scope: open the project selector and choose specific **reports** or **records**. Questions then use only those documents, so you can "talk" to a subset (e.g. one report or a few records) instead of the whole project. **When to use Ask Project:** * Summarize or compare findings across several reports * Find where a theme or quote appears in the project * Ask follow-up questions about a single report or a few records * Check claims against the actual project content Answers are grounded in your project data; citations link back to the source so you can verify and reuse the information. ## Manage your workspace from chat The Research Assistant can read and change your Aseed workspace directly from the conversation. Refer to projects and records by name — the assistant finds the right item itself and never asks you for internal IDs. **What you can ask for:** * **Explore your workspace** — list projects and their records, open transcripts and reports, check AI Interviewer rooms, or see your token balance. For example: "What projects do I have?" or "Show the records in Onboarding Research". * **Manage projects** — create a project, or update its name, description, status, research goals, and interview guide. For example: "Rename Onboarding Research to Onboarding Q3". * **Manage records** — rename records, move them between projects, archive or restore them, reset failed processing, and update record setup (goals, guide, notes, languages, participants). * **Generate reports** — preview the expected token cost, generate or regenerate single-record reports, and create or run project reports. **How it works:** 1. **Ask in plain language** — Describe what you want, including multi-step requests like "show the records in this project, then rename it". The assistant searches your workspace, resolves the right project or record, and completes each step in order. 2. **Confirm sensitive actions** — Archiving, resetting processing, and paid report generation show a confirmation card with the expected token cost before anything runs. Nothing is charged or changed until you confirm. 3. **See the results** — Completed actions appear as cards in the chat, and your project and record lists refresh automatically. Report generation from chat uses the same token balance and billing rules as the rest of the app. Preview actions are free. The assistant answers workspace requests in the language you write in. File upload, deletion, transcript editing, and token purchase are not available from chat. ## Generate research context with AI The Research Assistant can build a Research Context Brief by asking focused questions about your project. The brief includes 11 sections: metadata, decision framing, product context, goals, questions, hypotheses, participants, method, analysis, outputs, glossary, and limitations. Navigate to the Research Assistant (sidebar link or `/space/agent`). You'll see an empty state with suggestion buttons. Research Assistant empty state showing suggestion buttons Research Assistant empty state showing suggestion buttons You can start in two ways: * **Click the suggestion button**: Click **"Create Research Context"** in the empty state * **Type a message**: Ask the assistant to create a research context brief. For example: * "Create a research context brief for my project" * "Help me define research goals and hypotheses" * "I need to prepare a research context" You have two options: **Option 1: Answer questions interactively** The AI will ask you questions about: * Research type and stage * Decision framing (what decisions will be made) * Product or service context * Research goals and questions * Target participants and segments * Research method and protocol * Hypotheses to test * Analysis approach * Expected outputs Answer each question so the AI can build a complete brief. **Option 2: Provide materials** If you already have notes or materials, share them in your first message (or later when asked). The AI will extract what it can and ask follow-up questions only for missing details. **Tips for answering questions:** * **Choose your reasoning mode**: Switch between **Fast** (2 tokens) and **Thinking** (5 tokens). Use Fast for most tasks and Thinking for complex cases. * **Skip questions if needed**: If you don't know the answer, click the **Skip** button. The AI will ask alternative questions. * **Long messages are automatically collapsed**: If your message is longer than 500 characters, it will be collapsed with a "Show more" button. Click to expand and see the full message. After gathering enough information, the assistant will show a summary. Review it and confirm to generate the research context brief. Once generated, you'll see: 1. **Preview card in chat** — A card showing the first few lines of the brief with a **View** button 2. **Full brief panel** — Click **View** to open the complete brief in a panel on the right side Use the **Save** button in the brief panel to: * **Download as Markdown** — Save the brief as a `.md` file * **Copy to clipboard** — Copy the brief text for pasting elsewhere * **Save directly to a project** — Select a project from the dropdown to attach the brief to that project's Research Goals field Save dropdown menu showing Download, Copy options and project list with badges Save dropdown menu showing Download, Copy options and project list with badges When you save the brief to a project, it populates the Research Goals field in that project. If the project already has research goals, you'll be asked to confirm overwriting them. Projects with research context show a **"Has context"** badge. Projects without it show **"No context"**. ## Token usage and cost The Research Assistant uses tokens for each assistant message when generating a research context brief. You can choose between two reasoning modes: **Cost:** 2 tokens per assistant message Use Fast mode for quick responses and standard brief generation. This mode provides fast, efficient answers suitable for most use cases. **Cost:** 5 tokens per assistant message Use Thinking mode for more complex research scenarios that require deeper analysis and reasoning. This mode provides more thorough responses and better handles nuanced requirements. You can switch between Fast and Thinking at any time with the mode selector. Use Fast for speed and Thinking for deeper analysis. Tokens are charged only for assistant messages. **Example:** If the AI asks 10 questions and you answer each one, that's 10 assistant responses. In Fast mode, this costs 20 tokens (10 × 2). In Thinking mode, this costs 50 tokens (10 × 5). Your questions don't cost tokens. For more details about token usage and costs, see [Token usage](/account/usage). ## How to add research context manually Inside your project, scroll to the section below the project header that contains **Research Goals** and **Interview Guide**. Project page showing Research Goals and Interview Guide cards Project page showing Research Goals and Interview Guide cards Click on the **Research Goals** card. In the modal, describe: Research Goals modal showing text area for entering research goals Research Goals modal showing text area for entering research goals * What you're trying to learn * Questions you want to answer * Hypotheses you want to test * Product or service context Click **Save** to store your goals. Click on the **Interview Guide** card. You can: * Paste your interview script or topic list * Use a guide created with the [Interview Guide Builder](/interviews/guide-builder) - you can save AI-generated guides directly to projects * Write the guide manually Click **Save** to store your guide. If you generated an interview guide using the AI Agent, you can save it directly to your project from the guide panel using the **Save** button. Interview Guide modal showing text area for entering interview guide Interview Guide modal showing text area for entering interview guide After saving, the context appears in the cards. Click **View** (or click the card) to see the full content. Click **Edit** to make changes. Describe what you want to learn from the interviews. Include: * Research objectives * Questions you want answered * Hypotheses to test * Product or service context * Any specific focus areas Provide the structure of your interviews. Include: * Opening questions * Main discussion topics * Follow-up questions * Closing questions ``` Product Description: A mobile banking app with instant transfer feature. Research Goal: Understand customer satisfaction with the new feature, focusing on challenges and emotions. Additional: Interested in frustrations and positive feelings while using the feature. ``` ``` Opening: - Thank you for participating - Explain purpose and duration - Confirm recording permission Main Questions: 1. Tell me about your experience with [feature] 2. What challenges do you face? 3. How do you currently solve this? 4. What would make this easier? Closing: - Any additional thoughts? - Thank you for your time ``` ## Documents (Coming soon) The Documents card is currently in development. This feature will allow you to upload supporting documents that provide additional context for analysis. ## How context is used Research goals and interview guide are used as the default context for AI interview links in this project. Research goals and interview guide are automatically included when generating reports. Context is applied to all records in batch operations. Context helps synthesize insights across multiple interviews. Better context produces more relevant insights. ## Best practices Write goals as outcomes, for example "Understand why users abandon onboarding" rather than "Learn about onboarding." Keep interview guides structured but flexible. Include main topics and example questions, but allow for natural conversation flow. Update context as your research evolves. If your goals change, update the Research Goals to reflect the new focus. Use [Interview Guide Builder](/interviews/guide-builder) to create structured guides for your research. You can save AI-generated guides directly to the project. For new projects, use the Research Assistant to generate a research context brief. The assistant guides you through required sections and creates a document you can save directly to the project. Select **Fast** mode (2 tokens) for quick responses and standard brief generation. Use **Thinking** mode (5 tokens) when you need deeper analysis for complex research scenarios. You can switch modes at any time during the conversation using the mode selector in the input area. If you have existing research materials, documentation, or notes, you can provide them in your first message. The AI will analyze the materials and extract information, asking only follow-up questions about missing or unclear details. This can save time compared to answering questions one by one. If you don't know the answer to a question, click the **Skip** button on the question card. The AI will ask alternative questions to gather the information it needs. Skipping is useful when you haven't decided on a particular aspect yet or the question doesn't apply to your research. You can ask the assistant to modify an existing research context brief. For example: * "Add more details about hypotheses" * "Update the participant segments" * "Change the analysis approach to focus on JTBD" * "Make the brief shorter" The AI will regenerate the brief based on your modifications. The assistant uses validation to ensure your research context brief is complete. If important information is missing, the AI will ask follow-up questions with different priorities: * **Must** questions: Critical information needed before generation * **Should** questions: Helpful but not required The AI prioritizes "must" questions and won't ask for confirmation to generate until all critical information is collected. If there's an error during generation (e.g., LLM service unavailable), the system uses a fallback template to create the brief from collected data. Fallback documents are marked with "(fallback)" in the title and include a warning message. While functional, fallback documents may lack some contextual refinement. You can regenerate the brief when the service is available. ## Force specific tool calls You can force the Research Assistant to use a specific tool for your request. This ensures your message is processed with the right context and capabilities. You can select an action in two ways: **Option 1: Use the action button** * Click the **`+`** button in the input toolbar * Select an action from the dropdown menu: * **Research Assistant**: Force the assistant to create research context briefs * **Interview Guide**: Force the assistant to generate interview guides * **Ask Project**: Force the assistant to answer using project documents (with citations) * **Documentation**: Force the assistant to answer questions about Aseed **Option 2: Use slash commands** * Type **`/`** in the message input * A menu appears with the same action options * Select an action to apply it to your message The selected action appears as a badge next to the input. You can remove it by clicking the badge. Type your message and send it. The AI will process your request using the selected tool, ensuring the response is tailored to that specific function. Forcing a tool is especially useful when you want to: * Ensure your research context request uses the Research Assistant tool * Make sure your guide request uses the Interview Guide tool * Get answers grounded in project documents using Ask Project * Get documentation-specific answers using the Documentation tool When an action is selected, messages are marked with a badge indicating which tool is being used (e.g., "Context Builder", "Guide Builder", "Ask Project", "Documentation"). ## Ask questions about Aseed The Research Assistant can answer questions about Aseed features, workflows, and best practices. Click **"Ask About Service"** in the empty state or ask questions like: * "How do I create a project?" * "What report types does Aseed support?" * "How does batch generation work?" * "How do I export reports?" You can also force documentation mode by selecting the **Documentation** action before asking your question. This ensures the AI uses the documentation tool to provide accurate, up-to-date answers. Messages with documentation answers are marked with a **"Documentation"** tag to indicate they're based on Aseed documentation. ## Related topics * [Create a project](/projects/create) * [AI Interviewer](/projects/ai-interviewer) * [Create interview guide](/interviews/guide-builder) * [Upload records](/projects/upload-records) * [Batch generation](/projects/batch-generation) * [Generate single reports](/reports/single) * [Create project reports](/reports/project) * [Token usage](/account/usage) # Create a project Source: https://docs.aseed.ai/projects/create Set up a new project to organize interviews, context, and reports. ## Overview A project is your research workspace. It holds interviews, context, and reports in one place. You can create a project with or without files. ## How to create a project Click **Create Project** on the Projects page or in the sidebar. Projects page with Create Project button visible in header Projects page with Create Project button visible in header Type a clear project name (up to 128 characters). The name should help you identify the research project at a glance. Create Project modal showing project name input field Create Project modal showing project name input field You can add interview files during project creation: * Click **Add files to the Project** or drag and drop files * Remove files before creating if needed Create Project modal showing file upload area with drag and drop zone Create Project modal showing file upload area with drag and drop zone **Supported formats:** * **Audio**: MP3, WAV, M4A, OGG * **Video**: MP4, MOV, AVI, WebM * **Text**: TXT, MD, SRT, VTT **File size limits:** * **Minimum**: 1KB for text files, 1MB for audio/video files * **Maximum**: 5GB per file Click **Create Project**. Aseed creates the project immediately, starts file upload in the background, and redirects you to the project page. Project page after creation showing project header and upload progress Project page after creation showing project header and upload progress ## What happens after creation The project appears in your Projects list immediately. If you added files, they upload asynchronously in the background. You can see upload progress on the project page. Files are automatically linked to the project. ## Best practices Use a naming pattern like "Product - Study - Month" so projects are easy to scan in the list. Create the project first, then add files later if you want to set up structure before upload. If file upload fails, you'll see a notification. You can upload the files again from the project page. ## Related topics * [Edit project details](/projects/edit) * [Manage projects](/projects/manage) * [Upload records to project](/projects/upload-records) * [Add research context](/projects/context) * [AI Interviewer](/projects/ai-interviewer) * [Create project reports](/reports/project) # Edit project Source: https://docs.aseed.ai/projects/edit Update project name, description, and status to keep your research organized. ## Overview Edit project details to reflect changes in your research focus or to organize projects by status. You can update the project name, description, and status (New, Opened, Closed) directly from the project page. ## How to edit a project Navigate to the project you want to edit from the Projects page. Click on the project title at the top of the page. The title becomes editable. Type the new name and press Enter or click outside to save. Press Escape to cancel. Project page showing editable project name field in edit mode Project page showing editable project name field in edit mode Click on the description text (or "No Description" if empty). Type your description and press Enter or click outside to save. Press Escape to cancel. Project page showing editable description field in edit mode Project page showing editable description field in edit mode Click the status badge next to the project title. Select from: * **New**: Recently created projects * **Opened**: Active projects you're working on * **Closed**: Completed or archived projects Project page showing status badge and status selection dropdown Project page showing status badge and status selection dropdown ## Project statuses Recently created projects that haven't been started yet. Active projects where you're currently conducting research or generating reports. Completed projects or projects you're no longer actively working on. Status helps you filter projects in the Projects list and separate active work from completed research. ## Best practices Keep project names concise but descriptive. Update them if the research focus changes significantly. Use descriptions to add context that isn't obvious from the name, such as research timeline or key stakeholders. Update status as you progress through your research workflow to keep your project list organized. ## Related topics * [Create a project](/projects/create) * [Manage projects](/projects/manage) * [Delete project](/projects/manage#delete-project) # Manage projects Source: https://docs.aseed.ai/projects/manage Organize and navigate your projects using filters, search, and status management. ## Overview Use the Projects page to organize and find research work by status. ## How to manage projects Open **Projects** in the sidebar. Cards show project name, status, record count, and report count. Projects page showing grid layout of project cards with names, statuses, and counts Projects page showing grid layout of project cards with names, statuses, and counts Use the tabs at the top to filter projects: * **All Projects**: Shows every project regardless of status * **New**: Projects with "New" status * **Opened**: Active projects with "Opened" status * **Closed**: Completed projects with "Closed" status Projects page showing status filter tabs at the top Projects page showing status filter tabs at the top Click on any project card to open the project detail page where you can view records, reports, and context. Click **Create Project** button in the header to start a new research project. ## Project cards Each project card displays: * Project title * Status badge (New, Opened, or Closed) * Number of records (interviews) in the project * Number of project reports generated Recently created projects that haven't been started yet. Active projects you're currently working on. Completed or archived projects. ## AI Interviewer in projects Each project includes an **AI Interviewer** section for voice interview links. Create links, configure settings, monitor statuses, and track completed sessions as project records. AI Interviewer links depend on your project context. Keep **Research Goals** and **Interview Guide** updated for better interview quality. If you're an admin, you'll see an additional **User Projects** section below your own projects: * Search projects by owner email or project name * View all projects across all users * Use the same status filters (All, New, Opened, Closed) ## Delete project Deleting a project permanently removes it. Your records (interviews) remain safe and accessible, but they will no longer be organized under this project. In the project detail page, click the settings icon (⚙️) in the header. Select **Delete Project** from the dropdown menu. Project page showing settings dropdown menu with Delete Project option Project page showing settings dropdown menu with Delete Project option Review the warning message and click **Delete Project** to confirm. The project will be permanently deleted, and you'll be redirected to the Projects page. Delete Project confirmation dialog with warning message Delete Project confirmation dialog with warning message ## Best practices Use status filters to separate active projects from completed research. Keep project names consistent with a naming pattern to make scanning easier. Regularly update project statuses to keep your workspace organized as projects progress. ## Related topics * [Create a project](/projects/create) * [Edit project](/projects/edit) * [AI Interviewer](/projects/ai-interviewer) * [Upload records](/projects/upload-records) * [Research Assistant](/projects/context) * [Create project reports](/reports/project) # Manage records Source: https://docs.aseed.ai/projects/manage-records Rename, archive, delete, or remove records from your project. ## Overview Manage individual records in your project. You can rename records for better organization, archive records you don't need right now, remove records from the project, or permanently delete them. ## How to manage records Navigate to the project containing the records you want to manage. In the **Project Records** section, click the three-dot menu (⋯) next to any record to see available actions. Project Records section showing three-dot menu next to a record Project Records section showing three-dot menu next to a record Select from the dropdown menu: * **Rename**: Change the record name * **Remove from Project**: Unlink the record from this project (record remains in your workspace) * **Archive**: Move the record to the Archived tab * **Unarchive**: Restore an archived record (available in Archived tab) * **Delete Record**: Permanently delete the record ## Record actions * Click **Rename** from the record menu * Enter the new name in the modal * Click **Save** to confirm * Useful for organizing records with clearer names **To archive:** * Click **Archive** to move a record to the Archived tab * Archived records are hidden from the main Uploaded tab * Use archiving to declutter your active records list **To unarchive:** * Switch to the **Archived** tab * Click the three-dot menu on an archived record * Select **Unarchive** to move it back to Uploaded * Click **Remove from Project** to unlink the record from this project * The record remains in your workspace and can be added to other projects * Useful when a record was added to the wrong project Deleting a record permanently removes it from your workspace. This action cannot be undone. All transcripts and reports associated with the record will also be deleted. * Click **Delete Record** from the menu * Confirm the deletion in the dialog * The record and all its data will be permanently removed ## Viewing archived records * Switch to the **Archived** tab in Project Records * View all archived records for the project * Use the same actions (unarchive, delete, etc.) on archived records ## Best practices Rename records immediately after upload with descriptive names that include respondent information or interview date. Archive records you've completed analyzing but want to keep for reference. This keeps your active list focused on current work. Use "Remove from Project" if you accidentally added a record to the wrong project. The record stays available for other projects. Only delete records when you're certain you don't need them. Consider archiving instead if you might need them later. ## Related topics * [Upload records](/projects/upload-records) * [Batch generation](/projects/batch-generation) * [Generate single reports](/reports/single) # Upload records Source: https://docs.aseed.ai/projects/upload-records Add interview files to your project for transcription and analysis. ## Overview Upload interview recordings or transcripts to your project. After upload, you can transcribe media files and generate reports. **Audio**: MP3, WAV, M4A, OGG\ **Video**: MP4, MOV, AVI, WebM\ **Text**: TXT, MD, SRT, VTT **Minimum**: 1KB (text) or 1MB (media)\ **Maximum**: 5GB per file ## How to upload records Navigate to the project where you want to add records. In **Project Records**, click **Upload Records**. You can: * Click to browse and select files * Drag and drop files into the upload area * Select multiple files at once Project Records section showing Upload Records button Project Records section showing Upload Records button After selecting files, track progress for each file. You can: * Cancel individual uploads by clicking the progress indicator * See upload percentage in real-time * Files appear in the records list as they upload Project Records section showing file upload progress indicators Project Records section showing file upload progress indicators When upload is complete, records appear in the **Uploaded** tab. Then continue with transcription or report generation. ## Upload behavior Files upload asynchronously so you can continue working. Real-time upload progress shown for each file. Retry failed uploads from the records list. Files are automatically linked to the project. ## Best practices Use clear file names that help you identify respondents later, for example: "Interview\_John\_Doe\_2024-01-15.mp4" Upload files in batches rather than one at a time for better efficiency. For text files, ensure they're properly formatted transcripts or notes that Aseed can process. ## Related topics * [Manage records](/projects/manage-records) * [Transcribe interviews](/interviews/transcribe) * [Generate single reports](/reports/single) * [Batch generation](/projects/batch-generation) # Quick Start: First Project Source: https://docs.aseed.ai/quickstart Create a project, prepare AI interviews, add recordings, and generate a shareable report in minutes. Use this quick start to create your first project report. ## Outcome * A project with interviews and transcripts * Single reports for each interview * A project report ready to share ## Steps Click **Create Project** in your workspace and name the study. Create Project modal showing project name input and file upload area Create Project modal showing project name input and file upload area Define your **Research Goals** and **Interview Guide** in the same setup step. Use the **Research Assistant** to generate both through guided Q\&A, or fill both fields manually. Research Assistant section showing Research Goals and Interview Guide cards Research Assistant section showing Research Goals and Interview Guide cards Clear goals and a clear guide lead to sharper interviews and better reports. Open **AI Interviewer** in the project, create links, and send one link to each respondent. **Learn more:** [AI Interviewer](/projects/ai-interviewer) Add past interviews from outside Aseed (audio, video, or text) in **Project Records**. Project Records section with Upload Records button Project Records section with Upload Records button Generate transcripts for audio/video files. Review and edit transcripts as needed. **Learn more:** [Transcribe interviews](/interviews/transcribe) and [Edit transcripts](/interviews/edit) Click **Generate Reports** and start with **Transcript** and **Q\&A** for each interview. See [Report types](/reports/report-types) to understand what each report contains. These reports become the base material for your project report. Click **Add Report**, choose a preset or custom structure, and generate the report. Report setup page showing preset templates Report setup page showing preset templates After you have the reports you need, use **Ask Project** in the [Research Assistant](/projects/context): select your project and ask questions to clarify or interpret findings. Answers are grounded in your project documents with citations. Share a public link or export the report. ## Next steps Learn how Aseed differs from general AI assistants. See the full workflow and links to detailed guides. Need help? Email [team@aseed.ai](mailto:team@aseed.ai). # Build a custom report Source: https://docs.aseed.ai/reports/custom Design your own report structure and prompts. ## Overview Custom reports let you define the exact sections and questions you want Aseed to answer when creating project reports. Build your own structure to synthesize insights from multiple interviews according to your specific research needs. Define exactly which sections and prompts to include in your synthesis. Write your own prompts or choose from system-provided section templates. Organize sections in any order that makes sense for your research. Tailor the synthesis to answer your unique research questions and frameworks. ## How to build custom reports In your project, navigate to the **Project Reports** section and click **Create Report**. In the report setup interface, click on the **Custom** tab to access the custom structure builder. Custom tab showing the custom structure builder interface Custom tab showing the custom structure builder interface Click **Add Section** to create a new section. You can choose from system-provided section templates (like "Key Insights", "Pain Points", "Recommendations") or create a completely custom section with your own prompt. System sections provide proven prompts that work well for common analysis needs. Use them as starting points and customize as needed. For each section, write a clear, specific prompt that defines what you want Aseed to analyze or answer. Good prompts are: * Specific to your research questions * Clear about the expected output * Tied to your research goals Custom section editor showing prompt input field Custom section editor showing prompt input field Drag sections up or down to reorder them. The order determines how sections appear in the final report. Organize sections logically, starting with overview sections and moving to detailed analysis. Consider the flow of your report: start with summaries and key insights, then move to detailed analysis, and end with recommendations or action items. Review your complete structure to ensure all sections are in the right order and prompts are clear. Click **Save** to save the custom structure. Complete custom structure showing multiple sections in order Complete custom structure showing multiple sections in order Choose which interview records to include in the synthesis, then click **Generate** to create the project report using your custom structure. ## System sections You can use these system-provided section templates as starting points: * **Summary / TL;DR** - Executive summary of findings * **Key Insights** - Major discoveries and insights * **Pain Points** - User frustrations and problems * **Unmet Needs** - Desires and unmet requirements * **Recommendations** - Actionable next steps * **Jobs-to-be-Done** - JTBD framework analysis * **Behavioral Patterns** - User behaviors and workarounds System sections come with proven prompts that work well for common analysis needs. You can use them as-is or customize the prompts to better fit your research. ## Best practices Keep custom prompts specific and tied to your research goals. Vague prompts lead to generic results, while specific prompts produce actionable insights. Begin with system sections to understand the structure, then customize prompts or add fully custom sections as needed. This saves time and ensures you're following proven patterns. Structure your report flow logically: overview first, then detailed analysis, then recommendations. This makes the report easier to read and more actionable. After generating a report with a custom structure, review the results and refine your prompts or section order. Custom structures improve with iteration. If you create a custom structure that works well, save it for reuse in future projects. Consistent structures enable easier comparison across research projects. ## Related topics * [Create a project report](/reports/project) * [Use report presets](/reports/presets) * [Generate single reports](/reports/single) - For individual interview analysis * [Report types](/reports/report-types) - Understand single report types and Custom report structure # Edit and regenerate reports Source: https://docs.aseed.ai/reports/edit Refine report output after review and regenerate with updated context. ## Overview Edit reports to improve clarity, fix issues, and align output with stakeholder needs. You can edit both single reports and project reports. Regenerate after major updates to apply new context. Refine individual interview reports to improve clarity and accuracy. Adjust aggregated reports that synthesize insights across multiple interviews. Regenerate reports to reflect transcript or context changes. Improve report quality before sharing. ## How to edit reports Navigate to the report you want to edit: * For single reports: Open the record detail page and go to the **Reports** tab * For project reports: Open your project and go to the **Project Reports** section Record detail page showing Reports tab with generated reports list Record detail page showing Reports tab with generated reports list Select the report you want to edit, or use the actions menu. Adjust content or structure based on your review. You may be able to: * Edit report text directly * Modify report structure * Update research context or prompts * Adjust report settings Report editor showing editable report content Report editor showing editable report content Save your edits. Changes are applied immediately to the report. If you've updated research context, transcripts, or prompts, regenerate the report to reflect these changes. Click **Regenerate** to create a new version with updated information. Report view showing Regenerate button or option Report view showing Regenerate button or option ## Editing tips ### Before regenerating * **Update transcripts** - Fix any errors in the transcript first * **Review research context** - Ensure Research Goals and Interview Guide are current * **Check prompts** - For Custom reports, refine your prompt if needed * **Verify settings** - Confirm language and other generation settings ### After editing * **Review changes** - Check that edits improve clarity and accuracy * **Validate against transcript** - Ensure edited content aligns with source material * **Share for feedback** - Get stakeholder input before finalizing ## Best practices Update research context or transcripts before regenerating for better results. The system uses the latest context when regenerating. Edit reports to improve clarity and remove any inaccuracies. Manual edits can significantly improve report quality. Regenerate reports after updating transcripts or research context to ensure reports reflect the latest information. For Custom reports, refine your prompt based on initial results, then regenerate for better alignment with your research questions. ## Related topics * [Report types](/reports/report-types) - Understand report structure and methodology * [Generate single reports](/reports/single) - Create reports for individual interviews * [Create a project report](/reports/project) - Generate aggregated reports from multiple interviews * [Review and edit transcripts](/interviews/edit) - Ensure transcript accuracy before generating reports # Use report presets Source: https://docs.aseed.ai/reports/presets Start with a predefined report structure. ## Overview Presets are ready-made report structures for project reports. Use them to generate consistent aggregated reports faster. Predefined report structures designed for common research scenarios and frameworks. Start generating reports immediately without building custom structures. Use the same structure across multiple projects for consistent analysis. Structures incorporate proven methodologies and best practices. ## How to use report presets In your project, navigate to the **Project Reports** section and click **Create Report**. In the report setup interface, click on the **Presets** tab to view available preset structures. Presets tab showing available preset structures Presets tab showing available preset structures Browse the available presets and choose the one that matches your research goal. Each preset includes a predefined structure with sections and prompts optimized for specific analysis types. Hover over or click on a preset to see its structure and included sections before selecting. After selecting a preset, review the structure to ensure it matches your needs. You can see all sections and prompts that will be used in the synthesis. Choose which interview records to include in the synthesis. Select interviews that are relevant to the preset's analysis type. Click **Generate** to create the project report using the selected preset structure. The system will synthesize insights from all selected interviews according to the preset's methodology. Project report generation using a preset structure Project report generation using a preset structure ## Available presets Common preset types include: * **General Synthesis** - Comprehensive analysis combining multiple report types * **JTBD Analysis** - Jobs-to-be-Done framework synthesis across interviews * **Persona Development** - Persona development from aggregated insights * **Theme Analysis** - Pattern and theme identification across interviews * **Pain Point Synthesis** - Aggregated pain point and frustration analysis The exact presets available may vary. Check the Presets tab in your project to see all available options. ## Best practices Use presets when you want speed and consistency across projects. They're ideal for teams that need standardized analysis approaches. Choose a preset that aligns with your research goals. Each preset is optimized for specific types of analysis and frameworks. Before generating, review the preset's structure to ensure it includes all sections you need. You can always switch to custom if a preset doesn't fit. For consistency, use the same preset structure across related research projects to enable easier comparison and synthesis. ## Related topics * [Create a project report](/reports/project) * [Build a custom report](/reports/custom) * [Generate single reports](/reports/single) - For individual interview analysis * [Report types](/reports/report-types) - Understand what each single report type contains # Create a project report Source: https://docs.aseed.ai/reports/project Synthesize insights across multiple interviews into one aggregated report. ## Overview Project reports are synthesized reports that aggregate insights from multiple interview records within your project. Unlike single reports that analyze one interview in isolation, project reports combine data from all selected records to identify patterns, themes, and insights across your entire research project. Combines insights from multiple interviews to reveal patterns and themes across your entire research project. Identifies common themes, pain points, and opportunities across all selected interviews. Use predefined presets or build your own custom structure to organize the synthesis. Provides a comprehensive view of your research project, not just individual interviews. ## How to create a project report Navigate to the project containing the interviews you want to synthesize. In your project, scroll to the **Project Reports** section and click **Create Report** or **Generate Report**. Project Reports section showing Create Report button Project Reports section showing Create Report button Select a preset from the **Presets** tab or build a custom structure in the **Custom** tab. Presets provide ready-made structures, while custom lets you define your own sections and prompts. Project report setup interface showing Presets and Custom tabs Project report setup interface showing Presets and Custom tabs Choose which interview records to include in the synthesis. You can select all records or specific ones that share common themes or research questions. Set language options and review any additional settings. If using a custom structure, ensure all sections and prompts are configured correctly. Click **Generate** to start the synthesis process. The system will analyze all selected interviews and create an aggregated report based on your chosen structure. Project report generation in progress Project report generation in progress ## Key differences * Analyze a single interview record in isolation * Focus on one respondent's insights * Generated per interview from transcripts * Foundation for project synthesis * Synthesize data from multiple records * Reveal patterns and themes across your entire project * Combine insights from all selected interviews * Use presets or custom structures for organization ## Best practices Review single reports first so the synthesis is clean. Project reports work best when you've already generated and reviewed individual reports for the interviews you want to include. This ensures accurate transcripts and quality insights before aggregation. Select interviews that share common themes or research questions. Project reports are most valuable when synthesizing related interviews that address similar research goals or user segments. Start with presets when you want speed and consistency across projects. Presets provide proven structures that work well for common research scenarios. Use custom structures when you have specific research questions or frameworks that aren't covered by presets. Custom structures give you full control over the synthesis approach. Ensure your project has Research Goals and Interview Guide defined—they're automatically included in the synthesis context for better results. ## Related topics * [Report types](/reports/report-types) - Understand single report types used in project synthesis * [Use report presets](/reports/presets) * [Build a custom report](/reports/custom) * [Edit and regenerate reports](/reports/edit) * [Generate single reports](/reports/single) - Create individual reports before synthesis # Overview Source: https://docs.aseed.ai/reports/report-types Understand what each report type contains, its methodology, and structure. Aseed supports multiple report types for different analysis goals. Each type uses its own structure and method. ## Report types * **[Transcript](/reports/report-types/transcript)** - Raw text conversion from audio/video files. * **[Q\&A](/reports/report-types/qa)** - Structured question-answer pairs with citations. * **[General](/reports/report-types/general)** - Comprehensive profile, insights, and recommendations. * **[JTBD](/reports/report-types/jtbd)** - Jobs-to-be-Done framework analysis. * **[Persona](/reports/report-types/persona)** - Deep persona profile with motivations and pain points. * **[Custom](/reports/report-types/custom)** - Tailored analysis based on your specific prompt. ## Choosing the right report type Best for: Quick understanding of what was discussed and a base for further analysis. Best for: Complete respondent profile with insights and recommendations. Best for: Understanding fundamental user jobs and innovation opportunities. Best for: Deep persona development and behavioral insights. Best for: Answering targeted research questions or applying custom frameworks. ## Report generation process All reports (except Transcript) follow a two-stage process: 1. **Draft generation**: Creates initial report from transcript 2. **Refinement**: Validates against transcript, corrects errors, enhances insights This ensures accuracy and quality in the final output. Report type selection interface showing all available report types Report type selection interface showing all available report types ## Related topics * [Generate single reports](/reports/single) * [Edit reports](/reports/edit) * [Create project reports](/reports/project) # Custom Report Source: https://docs.aseed.ai/reports/report-types/custom Tailored analysis based on your specific research questions and prompt. ## What it is A **Custom Report** is a flexible, tailored analysis that adapts its structure and content based on your specific prompt. Unlike fixed-format reports, it designs the optimal report structure to answer your unique research questions. ## Methodology * **Dynamic structure**: Builds report sections based on your custom prompt * **Intelligence analysis**: Deconstructs your prompt to understand core questions and audience * **Section selection**: Chooses relevant sections from a palette of analysis frameworks * **Deep synthesis**: Goes beyond summarization to find why and connect patterns * **Business value translation**: Converts insights into business impact ## Structure The structure is dynamic and depends on your custom prompt. Common sections include: **Core Sections:** | Section | Description | | - | - | | **Summary / TL;DR** | Executive summary of findings | | **Data Confidence** | Scope and representativeness | | **Key Insights and Discoveries** | Major discoveries and findings | | **Evidence to Insight to Action** | Mapping table connecting quotes to insights to actions | | **Strategic Recommendations** | Actionable next steps | **UX Problem and Opportunity Sections:** | Section | Description | | - | - | | **Pain Points and User Frustrations** | User frustrations and problems | | **Unmet Needs and Desires** | Desires and unmet requirements | | **Feature Requests and Feedback** | User feedback and suggestions | | **Behavioral Patterns and Workarounds** | Workarounds and actual behaviors | | **Jobs-to-be-Done (JTBD)** | JTBD framework analysis | **Decision Context Sections:** | Section | Description | | - | - | | **Decision-Making Drivers** | What influences user decisions | | **Emotional Landscape** | Emotional factors and feelings | **Optional Sections (if requested):** | Section | Description | | - | - | | **Market Opportunity Analysis** | Market analysis and opportunities | | **Competitive Landscape** | Competitive analysis | | **User Journey Analysis** | Journey analysis | | **Mental Models** | User mental models | | **Risk and Opportunity Matrix** | Risk and opportunity assessment | Example Custom report showing dynamic structure based on custom prompt Example Custom report showing dynamic structure based on custom prompt ## What you get * **Tailored structure**: Report organized to answer your specific questions * **Deep analysis**: Strategic insights beyond surface-level observations * **Evidence mapping**: Clear connection between quotes, insights, and actions * **Business impact**: Every insight framed in terms of business value * **Actionable recommendations**: Specific next steps with checkboxes * **Minimum 5,000 characters**: Exhaustive, detail-rich analysis ## Best for * **Specific research questions**: Answer targeted questions not covered by standard reports * **Executive briefings**: Create reports tailored to stakeholder needs * **Custom analysis frameworks**: Apply your own methodology or framework * **Multi-faceted analysis**: Combine insights from different perspectives ## Related topics * [Generate single reports](/reports/single) * [Build custom reports](/reports/custom) * [Persona Report](/reports/report-types/persona) # General Report Source: https://docs.aseed.ai/reports/report-types/general Comprehensive profile, insights, and recommendations analysis. ## What it is A **General Report** provides a comprehensive analysis of the interview, structured into three main sections: Profile, Insights, and Recommendations. It's designed for product managers and researchers who need a complete understanding of the respondent. ## Methodology * **Profile analysis**: Extracts respondent demographics, goals, motivations, pain points, emotions, and tools * **Insight synthesis**: Identifies key findings, barriers, engagement levels, and expectations * **Actionable recommendations**: Provides specific steps for product and service improvements * **Evidence-based**: Every insight supported by quotes from the transcript with utterance citations ## Structure The General report includes three main sections: | Section | Description | | - | - | | **Profile Section** | General Info, Goals, Motivations, Pain Points, Emotions, and Tools | | **Insights Section** | Key Insights, Barriers, Engagement, and Expectations | | **Recommendations Section** | Actionable Steps, Product Improvements, and Service Enhancements | Example General report showing Profile, Insights, and Recommendations sections Example General report showing Profile, Insights, and Recommendations sections ## What you get Demographics, goals, motivations, pain points, emotions, and tools Key findings, barriers, engagement, and expectations (minimum 3 items each) Specific steps for product and service improvements (minimum 3 items each) Every insight linked to specific transcript utterances Recommendations tied to your research objectives ## Best for * **Comprehensive analysis**: Get a complete picture of the respondent * **Product development**: Understand user needs and pain points * **Strategic planning**: Identify opportunities and barriers * **Stakeholder communication**: Share structured insights with teams ## Related topics * [Generate single reports](/reports/single) * [Q\&A Report](/reports/report-types/qa) * [JTBD Report](/reports/report-types/jtbd) # JTBD Report Source: https://docs.aseed.ai/reports/report-types/jtbd Jobs-to-be-Done framework with job stories, ODI scores, and recommendations. ## What it is A **JTBD (Jobs-to-be-Done) Report** analyzes the interview through the Jobs-to-be-Done framework. It identifies the fundamental jobs users are trying to accomplish and provides a structured analysis of their journey, desired outcomes, and opportunities for innovation. ## Methodology * **Jobs-to-be-Done framework**: Identifies core jobs and sub-jobs users want to accomplish * **Job Stories**: Structured format: When context, I want to action, So that outcome * **Outcome-Driven Innovation (ODI)**: Calculates opportunity scores for desired outcomes * **Job Map**: Visualizes the user's journey through job steps * **Forces of Progress**: Analyzes what drives users to switch solutions ## Structure The JTBD report includes: | Section | Description | | - | - | | **Executive Summary** | Main insights, key quotes, and action steps | | **Job Stories** | Hierarchical list of Jobs and SubJobs | | **Job Map** | Step-by-step journey visualization | | **Forces of Progress** | Analyzing switching triggers | | **Current Alternatives and Context** | Alternatives and context | | **Desired Outcomes (ODI)** | Opportunity scores for innovation priorities | | **Barriers, Frictions and Risks** | Obstacles and risks | | **Evidence-based Insights** | Insights supported by quotes | | **Recommendations and Hypotheses** | Hypotheses with prioritization | | **Appendices** | Limitations and glossary | Example JTBD report showing Job Stories, Job Map, ODI scores, and recommendations Example JTBD report showing Job Stories, Job Map, ODI scores, and recommendations ## What you get * **Job Stories**: Complete When / I want to / So that narratives in first person * **Job hierarchy**: Core jobs with 2-4 sub-jobs each (maximum 2 levels) * **Job Map**: Step-by-step journey visualization * **ODI scores**: Calculated opportunity scores for innovation priorities * **Forces analysis**: Understanding what drives solution switching * **Prioritized recommendations**: Impact/Effort scoring for actionable next steps ## Best for * **Product strategy**: Understand fundamental user jobs * **Innovation opportunities**: Identify high-opportunity outcomes (ODI scores) * **Solution design**: Design products that help users accomplish jobs * **Competitive analysis**: Understand switching forces and alternatives ## Related topics * [Generate single reports](/reports/single) * [General Report](/reports/report-types/general) * [Persona Report](/reports/report-types/persona) # Persona Report Source: https://docs.aseed.ai/reports/report-types/persona Deep persona profile with motivations, pain points, and behavioral patterns. ## What it is A **Persona Report** creates a deep, actionable persona profile based on the interview. It synthesizes the respondent's characteristics, motivations, pain points, and behaviors into a strategic persona that guides product development and marketing decisions. ## Methodology * **Persona synthesis**: Combines demographics, context, and behavioral patterns * **Jobs-to-be-Done integration**: Identifies core jobs within the persona context * **Motivation analysis**: Deep dive into what drives user behavior * **Pain point mapping**: Identifies frustrations and their impact * **Behavioral patterns**: Documents workarounds and actual usage behaviors * **Ideal solution vision**: Describes the perfect solution from the user's perspective ## Structure The Persona report includes: | Section | Description | | - | - | | **Persona summary** | Memorable name and overview | | **Demographics and Background** | Background and context | | **Core Jobs-to-be-Done (JTBD)** | Jobs-to-be-Done with job stories | | **Key Motivations and Drivers** | Primary drivers of behavior with quotes | | **Major Pain Points and Frustrations** | Major frustrations and obstacles with quotes | | **Behaviors and Workarounds** | Actual behaviors and workarounds | | **The Ideal Solution** | Vision of the perfect product/service | | **Summary** | Key questions answered | Example Persona report showing persona profile, motivations, pain points, and ideal solution Example Persona report showing persona profile, motivations, pain points, and ideal solution ## What you get * **Complete persona profile**: Demographics, background, and context * **Core jobs**: 2-4 major jobs the persona wants to accomplish * **Motivations**: Primary drivers of behavior (with quotes and recommendations) * **Pain points**: Major frustrations and obstacles (with quotes and solutions) * **Behavioral insights**: Actual behaviors and clever workarounds * **Ideal solution**: Vision of the perfect product/service * **Strategic recommendations**: How to serve this persona better ## Best for * **Persona development**: Create detailed user personas for product teams * **Marketing strategy**: Understand what motivates and frustrates users * **Feature prioritization**: Focus on solving real pain points * **User experience design**: Design for actual behaviors, not assumptions ## Related topics * [Generate single reports](/reports/single) * [JTBD Report](/reports/report-types/jtbd) * [Custom Report](/reports/report-types/custom) # Q&A Report Source: https://docs.aseed.ai/reports/report-types/qa Structured question-answer pairs organized by topic with citations. ## What it is A **Q\&A Report** extracts and organizes all questions and answers from the interview into a structured format. It preserves the conversational flow while making it easy to find specific information. ## Methodology * **Extraction-based**: Pulls questions and answers directly from the transcript * **Topic grouping**: Organizes Q\&A pairs into logical topics or sections * **Citation tracking**: Every question and answer includes utterance numbers for verification * **Light editing**: Removes fillers and transcription errors while preserving meaning ## Structure The Q\&A report follows this structure: | Section | Description | | - | - | | **Main summary** | Key insights at the report level | | **Topic sections** | Organized by topic with subsection summaries | | **Question and answer pairs** | Question and answer pairs with utterance citations | | **First-person answers** | Respondent's answers preserved in their voice | Example Q&A report showing topic sections with question-answer pairs and citations Example Q&A report showing topic sections with question-answer pairs and citations ## What you get Every question and answer from the interview Related questions grouped together Each question and answer linked to transcript line numbers Key insights at the report and subsection level Respondent's answers preserved in their voice ## Best for * **Quick reference**: Find specific questions and answers quickly * **Interview review**: See the complete conversation structure * **Quote extraction**: Easy access to respondent quotes with citations * **Topic analysis**: Understand what was discussed in each area ## Related topics * [Generate single reports](/reports/single) * [Transcript Report](/reports/report-types/transcript) * [General Report](/reports/report-types/general) # Transcript Report Source: https://docs.aseed.ai/reports/report-types/transcript Raw text conversion from audio/video files - the foundation for all other reports. ## What it is A **Transcript** is the raw text output from converting audio or video files to text. It's the foundation for all other reports - every analysis report requires a transcript first. ## Structure | Element | Description | | - | - | | **Plain text format** | Raw conversation text with speaker identification | | **Utterance numbers** | Each line or segment is numbered for reference | | **Speaker labels** | Identifies interviewer and respondent | | **Timestamps** | Optional timing information for each segment | Example transcript report showing numbered utterances with speaker labels Example transcript report showing numbered utterances with speaker labels ## When to use Generate a transcript before creating any other report type Read the raw conversation to understand what was discussed Use as a source of truth when reviewing other reports Make corrections to transcription errors before generating analysis reports ## How it's generated Transcripts are created using automated speech-to-text technology (AssemblyAI). The system: * Processes audio/video files * Identifies speakers * Converts speech to text * Numbers each utterance for citation in other reports Always review and edit your transcript before generating analysis reports. Accurate transcripts lead to better insights. ## Related topics * [Generate single reports](/reports/single) * [Edit transcripts](/interviews/edit) * [Q\&A Report](/reports/report-types/qa) # Generate single reports Source: https://docs.aseed.ai/reports/single Create per-interview reports like Transcript, Q&A, General, JTBD, Persona, or Custom. ## Overview Single reports analyze one interview record in isolation. Each report focuses on a single transcript and extracts insights specific to that interview. These reports are the building blocks for project-level synthesis—use them to understand individual interviews before creating aggregated project reports. Each report analyzes one interview transcript in detail, extracting insights specific to that respondent. Single reports provide the building blocks for project-level reports that synthesize insights across multiple interviews. Generate Transcript, Q\&A, General, JTBD, Persona, or Custom reports for each interview. Understand each interview in isolation before aggregating findings across your research project. ## How to generate single reports Navigate to the project containing the records you want to analyze. In the **Project Records** section, scroll to the bottom and click **Generate Reports** button. Project Records section showing Generate Reports button at the bottom Project Records section showing Generate Reports button at the bottom In the generation modal, select which records you want to generate reports for. You can select one or multiple records. Generate Reports modal showing record selection and report type options Generate Reports modal showing record selection and report type options Select the report types you need for each interview. You can select multiple types: * **Transcript** (always required for other reports) * **Q\&A** - Question and answer format * **General** - Comprehensive insights * **JTBD** - Jobs-to-be-Done analysis * **Persona** - Persona development * **Custom** - Custom analysis with your prompt Start with Transcript and Q\&A for most interviews. These provide a solid foundation and are cost-effective. Set language options and any custom prompts if you selected Custom reports. Review the token estimate before generating. Click **Generate** to start report generation. The modal closes, and you'll see progress indicators on each record. Project Records showing report generation progress indicators Project Records showing report generation progress indicators Reports are generated asynchronously. Wait for the status to change to "Finished". You can view reports from the record detail page or the project reports section. ## Report types Aseed generates six types of reports, each designed for specific analysis needs: Raw text conversion from audio/video files. Required foundation for all other reports. Structured question-answer pairs organized by topic with citations. Comprehensive profile, insights, and recommendations analysis. Jobs-to-be-Done framework with job stories, ODI scores, and recommendations. Deep persona profile with motivations, pain points, and behavioral patterns. Tailored analysis based on your specific research questions and prompt. For detailed information about each report type, including methodology, structure, and what you'll receive, see [Report types](/reports/report-types). ## Report generation process Most reports (except Transcript) go through draft generation and refinement stages for accuracy. Research Goals and Interview Guide from your project are automatically included in report context. Tokens are consumed when generation starts. Check the estimate before generating. Reports generate in the background so you can continue working. ## When to use single reports * **Analyze individual interviews in detail** - Get deep insights from each respondent * **Extract specific insights** - Focus on one interview's unique findings * **Review interview quality** - Assess content and accuracy before aggregation * **Generate reports for standalone interviews** - Create reports for interviews that don't need synthesis * **Build foundation for project reports** - Create single reports first, then synthesize into project reports ## Best practices Start with Transcript and Q\&A reports for most interviews. These provide a solid foundation and are cost-effective. You can always add other report types later if needed. Review and edit transcripts before generating reports. Accurate transcripts lead to better insights. Fix speaker names and correct any transcription errors to improve report quality. Use General reports when you need comprehensive analysis of a single interview with insights and recommendations. This report type provides a complete respondent profile. Generate JTBD or Persona reports when you have clear research goals aligned with those frameworks. These specialized reports provide deep insights using established methodologies. Use Custom reports to answer specific research questions or apply frameworks not covered by standard report types. Provide a clear, detailed prompt for best results. Check your project's Research Goals and Interview Guide before generation—they're automatically included in the context for better results. Update them if your research focus has changed. ## Related topics * [Report types](/reports/report-types) - Detailed guide to each report type, methodology, and structure * [Review and edit transcripts](/interviews/edit) - Ensure transcript accuracy before generating reports * [Edit reports](/reports/edit) - Refine and regenerate reports after review * [Create a project report](/reports/project) - Synthesize insights from multiple single reports * [Batch generation](/projects/batch-generation) - Generate reports for multiple records at once # Export reports Source: https://docs.aseed.ai/sharing/export Download reports in DOCX or Markdown formats for presentations, editing, or archives. ## Overview Exporting lets you download reports in formats suitable for presentations, documentation, and offline access. You can export both single reports (per-interview) and project reports (aggregated) in DOCX or Markdown formats. Microsoft Word format with full formatting, ideal for presentations and documentation. Plain text format with Markdown syntax, perfect for version control and editing. Download reports for viewing and sharing without internet connection. Keep local copies of reports for archival or backup purposes. ## Export formats Aseed supports two export formats: | Format | Description | Best for | | - | - | - | | **DOCX** | Microsoft Word document format with full formatting | Presentations, documentation, sharing with stakeholders who need to edit or annotate | | **Markdown (.md)** | Plain text format with Markdown syntax | Version control, editing in text editors, integration with documentation systems | ## How to export single reports Single reports can be exported to DOCX format. Each report type (Transcript, Q\&A, General, Persona, JTBD, Custom) can be exported individually. Navigate to the record containing the report you want to export. Open the record from the Records page or from your project's records list. Record view showing report tabs and export button Record view showing report tabs and export button Click the **Export** button in the navigation menu or header. This opens a dropdown menu showing all available report types for export. Export dropdown showing available report types for DOCX export Export dropdown showing available report types for DOCX export Choose the report type you want to export from the dropdown menu. Only report types that have been generated are available for export (others show "Not available"). You can export multiple report types separately. Each export creates a separate DOCX file with the report type name in the filename. The system converts the report to DOCX format. This may take a few seconds depending on the report size. You'll see a loading indicator during the process. Large reports (over 8 MB) cannot be exported. If you encounter this limitation, consider exporting smaller sections or using Markdown format for project reports. Once the export is complete, the DOCX file automatically downloads to your default download location. The filename includes the record title and report type (e.g., "Interview\_John\_Doe - Q\&A Report.docx"). Success notification showing exported file download Success notification showing exported file download ## How to export project reports Project reports can be exported to both DOCX and Markdown formats. Project reports include aggregated insights from multiple interviews. Navigate to the project report you want to export. You can access project reports from your project's reports section or from the Project Reports page. Project report view showing export button Project report view showing export button Click the **Export** button in the navigation menu or header. This opens a dropdown menu with two options: "Export to .Docx" and "Export to .md". Export dropdown showing DOCX and Markdown options for project reports Export dropdown showing DOCX and Markdown options for project reports Select your preferred format: * **Export to .Docx** - For presentations and documentation with full formatting * **Export to .md** - For version control, editing, or integration with documentation systems DOCX format includes a header with project name, report title, and export date. Markdown format is plain text and can be easily edited in any text editor. The system processes the export: * **DOCX**: Converts Markdown content to Word format (may take longer for large reports) * **Markdown**: Generates plain text file (usually instant) DOCX export has a 60-second timeout. Very large project reports may exceed this limit. In such cases, use Markdown export instead. Once the export is complete, the file automatically downloads. The filename includes the project name, report title, and export date (e.g., "Product\_Research - Synthesis\_Report - 2024-01-15.docx"). Success notification showing exported project report file download Success notification showing exported project report file download ## Export format details ### DOCX format DOCX (Microsoft Word) format preserves all formatting, structure, and styling from your reports. This format is ideal for: * **Presentations** - Share with stakeholders in a professional format * **Documentation** - Include in project documentation * **Editing** - Recipients can edit and annotate the document * **Printing** - Professional print-ready format **Features:** * Full Markdown formatting preserved (headings, lists, tables, links) * Support for admonition blocks (info, warning, tip, note) * Automatic header with report title and metadata * Language-specific formatting (locale support) **File naming:** * Single reports: `[Record Title] - [Report Type].docx` * Project reports: `[Project Name] - [Report Title] - [Date].docx` ### Markdown format Markdown (.md) format provides plain text with Markdown syntax. This format is ideal for: * **Version control** - Track changes in Git repositories * **Editing** - Edit in any text editor or Markdown editor * **Integration** - Use with documentation systems (MkDocs, Docusaurus, etc.) * **Lightweight** - Small file size, fast export **Features:** * Plain text format with Markdown syntax * Includes header with project name, report title, and export date * Compatible with all Markdown processors * Easy to convert to other formats **File naming:** * Project reports: `[Project Name] - [Report Title] - [Date].md` Markdown export is currently available only for project reports. Single reports can be exported to DOCX format. ## Export limitations and errors ### File size limits * **Maximum file size**: 8 MB (Markdown content before conversion) * **Timeout**: 60 seconds for DOCX conversion * If your report exceeds these limits, you'll see an error message ### Common errors | Error | Cause | Solution | | - | - | - | | **File too large (413)** | Report content exceeds 8 MB limit | Export project reports in Markdown format, or split into smaller sections | | **Conversion timeout (504)** | Export took longer than 60 seconds | Use Markdown format for very large reports, or contact support | | **Report not found (404)** | Report hasn't been generated yet | Generate the report first before exporting | | **Conversion error (500)** | Markdown format issue | Check the report content for formatting errors, regenerate the report | If you encounter size or timeout issues with DOCX export, try exporting to Markdown format instead. Markdown exports are faster and have no size limitations. ## Supported report types ### Single reports export All single report types can be exported to DOCX format. Each report type is exported as a separate file. | Report Type | Export Format | Notes | | - | - | - | | **Transcript** | DOCX | Raw transcript with speaker labels and utterance numbers | | **Q\&A Report** | DOCX | Question-answer pairs with citations | | **General Report** | DOCX | Complete profile with insights and recommendations | | **Persona Report** | DOCX | Persona profile with motivations and pain points | | **JTBD Report** | DOCX | Jobs-to-be-Done framework analysis | | **Custom Report** | DOCX | Custom analysis based on your prompt | Only generated reports can be exported. If a report type shows "Not available" in the export menu, generate that report type first. ### Project reports export Project reports can be exported to both DOCX and Markdown formats. Project reports include aggregated insights from multiple interviews. | Format | Available | Use Case | | - | - | - | | **DOCX** | Yes | Presentations, documentation, editing | | **Markdown** | Yes | Version control, text editing, integration | ## DOCX format features ### Admonition block support DOCX export supports custom admonition blocks in Markdown, which are converted to styled callout boxes in Word documents: * **Info blocks** (`ad-info`) - Blue information boxes * **Warning blocks** (`ad-warning`) - Yellow warning boxes * **Tip blocks** (`ad-tip`) - Green tip boxes * **Note blocks** (`ad-note`) - Gray note boxes These blocks appear in your reports and are preserved in the exported DOCX file with appropriate styling. ### Language and locale DOCX exports support language-specific formatting: * **Default locale**: ru-RU (Russian) * **Locale setting**: Automatically uses the report's language setting * **Formatting**: Language-specific date, number, and text formatting ### File structure Exported DOCX files include: * **Report header** - Report type and title * **Full content** - All sections, formatting, and citations preserved * **Metadata** - Record/project information embedded in document properties ## Differences: Single vs Project reports | Feature | Single Reports | Project Reports | | - | - | - | | **Available formats** | DOCX only | DOCX and Markdown | | **Export location** | Record page, Export dropdown | Project report page, Export dropdown | | **File naming** | `[Record Title] - [Report Type].docx` | `[Project] - [Report] - [Date].docx` or `.md` | | **Content** | Single interview analysis | Aggregated insights from multiple interviews | | **Header** | Report type and record title | Project name, report title, and export date | | **Size limits** | 8 MB, 60 sec timeout | 8 MB, 60 sec timeout (DOCX only) | ## Best practices Export after final edits so the shared version stays consistent. Make sure all edits, corrections, and updates are complete before exporting to avoid sharing outdated versions. Select the export format based on how the report will be used. DOCX is best for presentations and documents that need editing, while Markdown is ideal for version control and integration with documentation systems. Exported files automatically include the record/project name, report type/title, and date. The system generates descriptive filenames, but you can rename them after download if needed. Export important reports for archival purposes. This ensures you have local copies even if reports are deleted or modified in Aseed. Consider exporting both DOCX and Markdown versions for maximum flexibility. For maximum flexibility, consider both exporting and creating a public link. Exports provide offline access, while public links allow real-time viewing of the latest version. For very large project reports, use Markdown export to avoid size and timeout limitations. Markdown files are smaller and export faster than DOCX. For single reports, you can export each report type separately. This allows you to share specific analysis types (e.g., just Q\&A or just Persona) without exporting everything. ## Related topics * [Share reports publicly](/sharing/public) # Aseed MCP Source: https://docs.aseed.ai/sharing/mcp Connect Aseed to Cursor, Codex, Claude, ChatGPT, or another MCP client to read and manage projects, records, and report generation. Aseed MCP lets an AI client work with the Aseed data you can already access. You can search and read your workspace, manage projects and records, prepare report settings, preview token costs, and start record or project report generation. Use this endpoint: ```text theme={null} https://app.aseed.ai/mcp ``` Each user signs in with their own Aseed account through browser OAuth. Access follows that user's Aseed permissions, and ownership is checked again for every operation. Confirmed report generation uses the same Aseed token balance and pricing rules as generation in the Aseed app. Preview the cost before you approve a paid generation tool. Open Cursor's MCP install prompt with the Aseed endpoint prefilled. Copy the endpoint for clients that need manual configuration. ## Before you connect You need: * An Aseed account. * Access to the projects, records, or reports you want your AI client to use. * An MCP client that supports Streamable HTTP remote servers. * Browser-based OAuth support in the client. If your client asks for a transport type, choose HTTP or Streamable HTTP. Do not use an API key; Aseed MCP uses browser OAuth. ## Approve access after upgrading New MCP connections request all supported read and write permissions by default. During browser authorization, Aseed shows the project, record, and report-generation permissions that will be granted, including a warning that confirmed generation can spend Aseed tokens. If you connected Aseed MCP before version 1.5.1, remove or disconnect the existing Aseed server in your MCP client. Add `https://app.aseed.ai/mcp` again and start browser authentication. Confirm the requested read and write access. Existing grants are never expanded silently, so reconnecting is required to add write permissions to an older connection. An MCP client may explicitly request a narrower permission set. If a write tool reports a missing scope, reconnect and approve write access. ## Connect from your client Use the install card above, or add the server manually. Click [**Add to Cursor**](cursor://anysphere.cursor-deeplink/mcp/install?name=aseed\&config=eyJ1cmwiOiJodHRwczovL2FwcC5hc2VlZC5haS9tY3AifQ==) on this page. Cursor opens an install prompt for the `aseed` MCP server. Confirm that the server URL is: ```text theme={null} https://app.aseed.ai/mcp ``` When Cursor shows that Aseed needs authentication, complete the browser sign-in flow. Ask Cursor to search your projects, read a transcript, update research context, archive a record, or generate a report after previewing its token cost. Manual configuration: ```json theme={null} { "mcpServers": { "aseed": { "url": "https://app.aseed.ai/mcp" } } } ``` Add the remote server, then start the OAuth login flow. ```bash theme={null} codex mcp add aseed --url https://app.aseed.ai/mcp codex mcp login aseed ``` Codex opens your browser for Aseed authorization and stores the OAuth credentials after the callback completes. You can also add the server to `~/.codex/config.toml`: ```toml theme={null} [mcp_servers.aseed] url = "https://app.aseed.ai/mcp" enabled = true ``` Then run: ```bash theme={null} codex mcp login aseed ``` Claude supports custom connectors for remote MCP servers. In Claude, open **Settings** or **Customize**, then open **Connectors**. Choose **Add custom connector** or **Add connector**, depending on your plan and workspace settings. Use a clear name such as `Aseed` and enter: ```text theme={null} https://app.aseed.ai/mcp ``` Click **Connect**, sign in to Aseed in the browser, and enable the connector in the conversation where you want to use it. For Claude Code, use: ```bash theme={null} claude mcp add --transport http aseed https://app.aseed.ai/mcp ``` Then run `/mcp` inside Claude Code and select Aseed to authenticate. ChatGPT supports custom remote MCP apps in developer mode for eligible accounts. Open ChatGPT settings, go to **Apps**, and enable **Developer mode** if it is available for your account. In **Apps & Connectors**, create a new app from a remote MCP server. Use: ```text theme={null} https://app.aseed.ai/mcp ``` Complete the browser OAuth flow. After the app is connected, enable it in the chat where you want ChatGPT to use Aseed. Custom connector availability depends on your ChatGPT plan, workspace settings, and developer mode access. For any MCP-compatible client, configure a remote Streamable HTTP server: ```json theme={null} { "name": "aseed", "url": "https://app.aseed.ai/mcp", "transport": "http" } ``` The client must support browser OAuth. When it first calls Aseed MCP, the server returns an OAuth challenge. The client should open the authorization page, receive the callback, and send the bearer token on later MCP requests. To use write tools, the granted permissions must include the relevant write scope. ## What you can do ### Search and read your workspace * Search accessible projects, records, transcripts, reports, and token-balance data. * Fetch a result by its stable `aseed://` identifier. * List and read projects, records, transcripts, single-record reports, and project reports. * Read your current token balance and confirm which Aseed account is connected. * List AI Interviewer room metadata without exposing respondent access tokens. ### Manage projects * Create a project with a name and optional description, research goals, and interview guide. * Update a project's name, description, research goals, interview guide, or status (`New`, `Opened`, or `Closed`). ### Manage records * Rename an owned record. * Assign a record to an owned project or remove it from its current project. * Archive or restore a record. Archiving is reversible and never deletes the record. * Reset a failed record only through the safe `Error` to `Finished` transition. * Update research goals, interview guide, meeting notes, custom prompt, participant count and known names, source language, report language, and speech-to-text provider. * Poll the current report-generation pipeline status. ### Generate record reports You can prepare and generate `Q&A`, `General`, `JTBD (legacy)`, `JTBD`, `Persona`, and `Custom` reports. Generation settings can also include transcript generation, source and report languages, participants, research context, meeting notes, a custom prompt, and the STT provider. Validate the record state and settings, and return the exact expected Aseed token cost and current balance. Previewing does not charge tokens or start a job. Start generation or regeneration with `confirm: true` and a stable `idempotency_key`. Aseed uses the native report pipeline and billing transaction. Read the generation status until processing completes, then retrieve the generated reports. ### Generate project reports * List the system and personal prompts and presets available to your account. * Create a private project-report definition from owned records and selected prompts, with transcript or Q\&A context, an optional preset, expanded report context, and report language. * Preview context size, reasoning multiplier, exact token cost, and current balance in `fast` or `thinking` mode. * Confirm generation with a stable idempotency key, then poll the existing project-report read tool until content is available. ## Tool reference Most tools support `response_format`. Use `json` for structured output and `markdown` for a human-readable response. List tools also support pagination. ### Search, account, and balance | Tool | Capability | | - | - | | `search` | Search accessible projects, records, transcripts, reports, and balance data with optional scope and project filters. Returns bounded snippets and stable `aseed://` IDs. | | `fetch` | Fetch one accessible object by an `aseed://` ID and optionally read long content in character windows. | | `aseed_get_current_user` | Confirm which Aseed identity the MCP connection uses. | | `aseed_get_token_balance` | Read the current available Aseed token balance without claiming or spending tokens. | ### Projects | Tool | Capability | | - | - | | `aseed_list_projects` | List and search projects owned by the connected user. | | `aseed_get_project` | Read one owned project, including context, status, and record/report counts. | | `aseed_create_project` | Create an owned project. Identical retries with the same idempotency key return the same project. | | `aseed_update_project` | Update name, description, status, research goals, or interview guide. Omitted fields remain unchanged. | ### Records and record content | Tool | Capability | | - | - | | `aseed_list_records` | List accessible records, optionally filtered by project, text, status, file type, or archived state. | | `aseed_list_project_records` | List records in one owned project. | | `aseed_get_record` | Read record metadata, processing state, available versions, and report availability. | | `aseed_get_record_transcript` | Read an accessible transcript and optional version with character-window pagination. | | `aseed_get_record_report` | Read a generated `qa`, `general`, `jtbd`, `persona`, or `custom` single-record report and optional version. | | `aseed_rename_record` | Rename an owned, mutable record. | | `aseed_set_record_archived` | Archive or restore a record with `confirm: true`; this never deletes it. | | `aseed_move_record` | Assign a record to an owned project, or pass `project_id: null` to unassign it. | | `aseed_reset_record_status` | Apply the safe failed-record reset with `confirm: true`; arbitrary pipeline status changes are not available. | | `aseed_update_record_setup` | Update goals, guide, meeting notes, custom prompt, participants, languages, or STT provider without starting generation. | | `aseed_get_record_generation_status` | Read the current native generation pipeline status for an owned record. | ### Prompts, presets, and record generation | Tool | Capability | | - | - | | `aseed_list_prompts` | List system and personal prompts available for project-report generation. | | `aseed_list_presets` | List system and personal presets available for project-report generation. | | `aseed_preview_record_report_generation` | Validate new generation or regeneration and return exact expected cost and current balance without charging. | | `aseed_generate_record_reports` | Generate reports for an eligible record through native billing and processing; requires confirmation and an idempotency key. | | `aseed_regenerate_record_reports` | Regenerate reports for a finished record through native billing and processing; requires confirmation and an idempotency key. | ### Project reports | Tool | Capability | | - | - | | `aseed_list_project_reports` | List project-level synthesis reports for an owned project. | | `aseed_get_project_report` | Read one owned project report and use character windows for long content. Also use it to poll a generated report. | | `aseed_create_project_report` | Create a saved private project-report definition without starting generation or spending tokens. | | `aseed_preview_project_report_generation` | Preview context tokens, reasoning multiplier, exact expected cost, and balance for `fast` or `thinking` generation. | | `aseed_generate_project_report` | Start native project-report generation with confirmation and an idempotency key; charges the previewed amount. | ### AI Interviewer | Tool | Capability | | - | - | | `aseed_list_interview_rooms` | List room metadata for your projects, optionally filtered by project and status. Respondent access tokens are excluded. | ## What Aseed MCP does not do Aseed MCP does not currently: * Upload audio, video, or text files. * Delete projects, records, or reports. Records can only be archived and restored. * Edit transcript content. * Purchase, top up, or claim tokens. * Change public-sharing settings. * Create or manage AI Interviewer rooms. * Create, edit, or delete prompts and presets. * Perform admin or all-user operations. ## Working with long transcripts and reports Transcript and report tools support character windows: * `content_limit` controls how many characters are returned. The default is 50,000 and the maximum is 100,000. * `content_offset` starts reading from a later character position. * `contentWindow.hasMore` and `contentWindow.nextOffset` tell you when to request the next window. Example: ```json theme={null} { "record_id": "00000000-0000-4000-8000-000000000000", "content_limit": 50000, "content_offset": 0, "response_format": "json" } ``` ## Security model Aseed MCP follows these rules: * **Per-user access:** each user authenticates with Aseed and can only read or change objects available to that Aseed account. * **Scoped OAuth:** new connections request all supported read and write scopes by default, while clients can request a narrower grant. Existing grants are never expanded silently. * **Ownership checks:** project and record ownership is checked before every delegated operation. A missing or inaccessible object is not exposed through a write error. * **Explicit confirmation:** archive, safe status reset, and paid generation require `confirm: true`. * **Native billing:** report previews and execution use the same pricing and token transaction flow as the Aseed app. * **Idempotent retries:** creation and generation tools use stable idempotency keys to prevent duplicate objects, jobs, or token charges. * **No direct database writes:** MCP delegates mutations to native Aseed services, which enforce object state, ownership, and billing rules. * **OAuth only:** sign in through browser OAuth. Do not paste Firebase ID tokens, API keys, or passwords into client configuration. * **No respondent tokens:** AI Interviewer room metadata excludes respondent access tokens. * **Large-content caps:** transcript and report content is capped and paginated by character windows. Transcripts and reports may contain user-provided content. Treat returned content as data from your workspace, not as instructions for the AI client. ## Troubleshooting Complete the browser authorization flow. If the browser does not open, copy the authorization URL from the client and open it manually. Check that the Aseed account used during OAuth can access that project or record in the Aseed app. MCP access follows the signed-in user's permissions. Disconnect Aseed MCP, connect it again, and approve the displayed write permissions. Connections created before version 1.5.1 may still have a read-only grant. Call the matching preview tool first. Review the expected token cost and current balance, then repeat the generation request with `confirm: true` and a stable idempotency key. Add tokens in the Aseed app, then retry with the same settings. A failed balance check does not start processing or change the record setup. Reuse an idempotency key only for exactly the same request. Use a new key when you intentionally change project fields, report settings, selected records, prompts, or generation mode. Add the server manually in Cursor's MCP configuration using the JSON in the Cursor tab. Some environments do not register the `cursor://` protocol handler. Confirm that your account and workspace support developer mode and custom MCP apps. If the option is unavailable, use another MCP client or ask your workspace admin. Request the next content window using `contentWindow.nextOffset` as `content_offset`. ## Related resources * [Aseed projects](/projects/create) * [Records](/interviews/records) * [Project reports](/reports/project) * [Export reports](/sharing/export) * [Cursor MCP docs](https://docs.cursor.com/context/model-context-protocol) * [Claude custom connectors](https://support.claude.com/en/articles/11175166-how-do-i-connect-mcp-servers-to-claude-ai) * [Claude Code MCP docs](https://code.claude.com/docs/en/mcp) * [ChatGPT developer mode](https://developers.openai.com/api/docs/guides/developer-mode) # Share reports publicly Source: https://docs.aseed.ai/sharing/public Create public links to share records and reports with stakeholders without requiring Aseed accounts. ## Overview Public links allow you to share records and project reports with stakeholders who don't have Aseed access. Anyone with the link can view the content in a read-only mode without needing to sign in or create an account. Public links are perfect for sharing research findings with clients, executives, or team members. Stakeholders can view records and reports without creating an Aseed account or signing in. Simply copy and share the link via email, messaging, documentation, or any communication channel. Links are unique and can be disabled at any time. You maintain full control over access. Public links provide view-only access—recipients cannot edit, delete, or generate new reports. ## What can be shared publicly You can create public links for two types of content: | Content Type | Description | Public URL Format | | - | - | - | | **Single Records** | Individual interview records with all reports (Transcript, Q\&A, General, Persona, JTBD, Custom) | `/space/records/public/{recordId}` | | **Project Reports** | Aggregated project reports with insights from multiple interviews | `/space/projects/public/{projectId}/reports/{reportId}` | Public links work for both single records and project reports. Choose the content type that best fits what you want to share with stakeholders. ## How to share single records publicly Single records can be shared publicly, giving access to all reports (Transcript, Q\&A, General, Persona, JTBD, Custom) for that specific interview. Navigate to the record you want to share. You can access records from the Records page or from your project's records list. Record view showing sharing options Record view showing sharing options Click the **Share** button or find the sharing option in the record menu. This opens the sharing modal with public link options. Sharing modal for records showing public link toggle Sharing modal for records showing public link toggle Toggle the **Public link** switch to enable public sharing. The link is immediately generated and active. When you enable public sharing, the link is automatically copied to your clipboard, making it easy to share right away. Sharing modal with public link enabled showing the link and copy button Sharing modal with public link enabled showing the link and copy button Click **Copy Link** to copy the public URL to your clipboard, then share it via email, messaging apps, or any communication channel. You can also copy the public link directly from the Records table by clicking the "Public" badge in the Public column. To revoke access, open the sharing modal again and toggle off **Public link**. The link will immediately stop working for all recipients. Disabling a public link is instant and affects everyone who has the link. Use this to maintain control over who can access your research. ## How to share project reports publicly Project reports can be shared publicly, giving access to aggregated insights from multiple interviews. Navigate to the project report you want to share. You can access project reports from your project's reports section or from the Project Reports page. Project report view showing sharing options Project report view showing sharing options Click the **Share** button or find the sharing option in the report menu. This opens the sharing modal with public link options. Sharing modal for project reports showing public link toggle Sharing modal for project reports showing public link toggle Toggle the **Public link** switch to enable public sharing. The system generates a unique link for this project report. Sharing modal with public link enabled showing the link and copy button Sharing modal with public link enabled showing the link and copy button Click **Copy Link** to copy the public URL to your clipboard, then share it with stakeholders. Include context when sharing project reports—explain the research objectives, key findings, or specific sections you want stakeholders to focus on. You can disable the public link at any time from the sharing modal. When disabled, the link immediately stops working for all recipients. Project owners can still access the report through their regular Aseed account even if the public link is disabled. ## What's hidden in public view For security and privacy, certain information is automatically hidden from public pages: | Hidden Information | Description | | - | - | | **Your name & email** | Personal account information is not visible to public viewers | | **Research objectives** | Project goals and research context are hidden from public access | | **AI Chat messages** | Messages you sent in the AI Chat are not visible on public pages | All report content (transcripts, insights, recommendations) is visible in public view. Only personal information and research context are hidden. ## Public page limitations Public pages have specific limitations to ensure security and prevent unauthorized actions: | Limitation | Description | | - | - | | **Read-only access** | Public viewers cannot edit, delete, or modify any content | | **No report generation** | Public pages do not support generating new reports or re-running analysis | | **No AI Chat access** | The AI Chat feature is not available on public pages | | **No export functionality** | Public viewers cannot export reports to DOCX or Markdown | | **Setup tab locked** | For project reports, the Setup tab is locked for non-owners on public pages | Public pages are designed for viewing and sharing research findings, not for active collaboration or editing. ## Quick copy from Records table You can quickly copy public links directly from the Records table: 1. Navigate to the **Records** page 2. Find the record you want to share 3. Look for the **Public** column 4. If the record is already public, click the **Public** badge to copy the link 5. If the record is not public, enable public sharing first through the record's sharing modal The Public column in the Records table shows a badge for records that are already public. Click the badge to instantly copy the public link. ## Best practices Review the record or report content before enabling public sharing to ensure it's ready for external stakeholders. Check for any sensitive information, incomplete sections, or incomplete analysis. Include a brief summary or context when you send the link so recipients know what to expect. Provide information about the research objectives, key findings, or specific sections you want stakeholders to focus on. Disable public links when they're no longer needed to maintain security and control access. This is especially important for records and reports containing sensitive research data or confidential information. Public links are ideal for sharing research findings with clients, executives, or team members who don't need full Aseed access but need to review insights and recommendations. For presentations or meetings, consider exporting the report to DOCX or Markdown in addition to sharing the public link. This provides offline access and allows for annotation or note-taking. While Aseed doesn't currently provide analytics on public link usage, you can track engagement by asking stakeholders for feedback or monitoring when links are accessed through your own communication channels. ## Differences: Single records vs Project reports | Feature | Single Records | Project Reports | | - | - | - | | **Public URL** | `/space/records/public/{recordId}` | `/space/projects/public/{projectId}/reports/{reportId}` | | **Content shared** | All reports for one interview (Transcript, Q\&A, General, Persona, JTBD, Custom) | Aggregated insights from multiple interviews | | **Access to tabs** | All report tabs visible | Setup tab locked for non-owners, Report tab visible | | **Copy from table** | Yes, via Public badge in Records table | No, only through sharing modal | | **Use case** | Share individual interview findings | Share project-level synthesis and insights | ## Related topics * [Export reports](/sharing/export) # What is Aseed? Source: https://docs.aseed.ai/what-is-aseed Aseed is a research-focused AI assistant built to turn interview data into structured insights and reports. ## A research tool built for a specific workflow Aseed is an AI-powered research assistant designed for customer and user interviews. It helps you move from raw recordings to structured insights and reports without manual synthesis. ## Why Aseed exists * Interviews are rich but hard to analyze at scale. * Teams need consistent insights, not ad-hoc summaries. * Research outcomes should be easy to share and reuse. ## How Aseed is different from general AI assistants General tools like ChatGPT or NotebookLM are great for open-ended conversation, but they are not built around the research workflow. Aseed is specialized and handles the full flow from project setup to report synthesis. | Focus | Aseed | General assistants (ChatGPT, NotebookLM) | | - | - | - | | Purpose | Research workflow and report generation | General chat, notes, and summaries | | Context | Analyzes the full project context you provide | Often works from prompts and retrieved snippets | | Workflow | Structured steps from interviews to reports | Ad-hoc conversations | | Output | Consistent report formats ready to share | Unstructured responses that need manual editing | Unlike notebook-style tools that rely on retrieval from source documents, Aseed is built to analyze the full context you provide across the project. ## What you can do with Aseed Define research goals, hypotheses, and interview structure without starting from scratch. Use AI to generate Research Context Briefs and interview guides through interactive Q\&A sessions, then save them directly to your projects. Convert audio and video interviews into accurate transcripts with speaker identification. Analyze interviews at scale without manually transcribing hours of recordings. Get structured analysis from each interview—identify key quotes, pain points, jobs-to-be-done, or persona characteristics. Choose from Transcript, Q\&A, General, JTBD, Persona, or Custom report types. See [Report types](/reports/report-types) for details. Combine insights from multiple interviews into one comprehensive report. Identify patterns, themes, and actionable recommendations across all your research data. ## How Aseed works Aseed follows a structured workflow from project setup to report synthesis. See the complete [Workflow guide](/workflow) for detailed step-by-step instructions. ## Where to start * New to Aseed? Start with [Getting Started](/). * Ready for results? Follow [Quick Start: First Project](/quickstart). # Workflow Source: https://docs.aseed.ai/workflow Understand the complete Aseed workflow from project creation to sharing reports. ## Summary Learn how Aseed differs from general AI assistants and what makes it unique for customer development research. Get your first project report in minutes. Follow the step-by-step guide to create a project, prepare AI interviews, collect responses, and generate reports. **Getting started fast?** Follow the [Quick Start guide](/quickstart) to create your first project and generate a report in minutes. For a deeper understanding of the workflow, continue reading below. ## The complete workflow Follow these steps to move from raw interviews to shareable insights: Set up a project to organize your research. Give it a clear name that describes your study, and optionally add interview files during creation. **Learn more:** [Create a project](/projects/create) Projects help you organize interviews, context, and reports in one place. You can create a project with or without files—files can be added later. Define your **Research Goals** and **Interview Guide** together. This is the preparation stage for AI interviews. Use the **Research Assistant** to generate both through guided Q\&A, or fill both fields manually in the project. **Learn more:** [Research Assistant](/projects/context) and [Create interview guide](/interviews/guide-builder) Keep goals and guide specific. Better context produces better interview questions and better reports. Open **AI Interviewer** in the project, create interview links, and send one link per respondent. **Learn more:** [AI Interviewer](/projects/ai-interviewer) Completed AI interviews are saved as project records automatically. Add existing audio, video, or text interviews that were recorded outside Aseed. **Learn more:** [Upload records to project](/projects/upload-records) or [View all records](/interviews/records) **Audio:** MP3, WAV, M4A, OGG\ **Video:** MP4, MOV, AVI, WebM\ **Text:** TXT, MD, SRT, VTT **Minimum:** 1KB (text) or 1MB (media)\ **Maximum:** 5GB per file Upload pre-written transcripts for text files, or generate transcripts for audio/video files. Review and edit before generating reports. **Learn more:** [Upload text transcripts](/interviews/text-transcripts), [Transcribe interviews](/interviews/transcribe), and [Edit transcripts](/interviews/edit) Accurate transcripts lead to better insights. Review speaker names and key terminology before report generation. Create per-interview reports to analyze individual interviews in isolation. Start with Transcript and Q\&A reports, then add General, JTBD, Persona, or Custom reports as needed. **Learn more:** [Generate single reports](/reports/single) and [Report types](/reports/report-types) Process multiple records at once using [Batch generation](/projects/batch-generation) to save time when working with many interviews. Synthesize insights across multiple interviews into one aggregated report. Project reports identify patterns, themes, and insights across your entire research project. **Learn more:** [Create a project report](/reports/project) Project reports combine data from all selected records. Make sure you've generated single reports for the interviews you want to include. **Ask Project:** Once you have reports and records in a project, you can use [Research Assistant](/projects/context) → **Ask Project** to ask questions about that content. Answers are grounded in your project documents with citations, and you can scope questions to the whole project or to specific reports and records. Publish your report with a public link or export it in various formats (PDF, DOCX, Markdown) for stakeholders. **Learn more:** [Share publicly](/sharing/public) and [Export reports](/sharing/export) ## Explore each part of the workflow Create, manage, and organize research projects. Projects are containers for interviews, context, and reports. Use the Research Assistant (including **Ask Project**) to generate context, interview guides, and to ask questions about project reports with citations. **Key topics:** [Create a project](/projects/create), [Research Assistant](/projects/context), [AI Interviewer](/projects/ai-interviewer), [Edit project](/projects/edit), [Manage projects](/projects/manage), [Upload records](/projects/upload-records), [Manage records](/projects/manage-records), and [Batch generation](/projects/batch-generation). View, manage, and upload interview records. The records table shows all your interviews with filtering, sorting, and bulk actions. **Key topics:** [Records page](/interviews/records), [Upload text transcripts](/interviews/text-transcripts), [Transcribe interviews](/interviews/transcribe), and [Edit transcripts](/interviews/edit). Analyze individual interviews with per-interview reports. Each report focuses on a single transcript and extracts insights specific to that interview. **Key topics:** [Generate single reports](/reports/single), [Report types](/reports/report-types), and [Edit reports](/reports/edit). Synthesize insights across multiple interviews into aggregated reports. Project reports identify patterns and themes across your entire research project. **Key topics:** [Create a project report](/reports/project), [Use presets](/reports/presets), and [Build custom reports](/reports/custom). Publish or export reports for stakeholders. Share public links or export reports in various formats. **Key topics:** [Share publicly](/sharing/public) and [Export reports](/sharing/export). ## Get your first result Follow the step-by-step guide to create a project, prepare AI interviews, add recordings, and generate your first report. Set up a project and describe your research goal. You can add files during creation or upload them later. **Comparing Aseed to general AI assistants?** Read [What is Aseed](/what-is-aseed) to understand how Aseed is specifically designed for customer development research and differs from general-purpose AI tools.