> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aseed.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Create interview guide
> 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`.
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
**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.
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
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
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