> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ansa.so/llms.txt
> Use this file to discover all available pages before exploring further.

# Documentation

> Create an AI assistant that helps users find answers in your documentation quickly and accurately.

export const Screenshot = ({src, alt}) => <img src={src} alt={alt} className="rounded-lg border border-gray-200" />;

## Overview

Ansa helps documentation teams:

* Provide instant answers from your docs
* Reduce support tickets for documented topics
* Surface relevant articles naturally
* Identify documentation gaps from user questions
* Handle questions your docs don't cover gracefully

<Screenshot src="/screenshots/chat.png" alt="Documentation assistant" />

## Knowledge Base Setup

### Indexing Your Documentation

Ansa supports multiple ways to index docs:

| Source Type      | Best For                             |
| ---------------- | ------------------------------------ |
| **Web Crawl**    | Public documentation sites           |
| **File Upload**  | PDFs, markdown files, internal docs  |
| **Text Sources** | Custom content, snippets             |
| **Q\&A Pairs**   | Common questions with vetted answers |

<Screenshot src="/screenshots/web-sources.png" alt="Web sources" />

### Web Crawling Tips

When crawling documentation sites:

1. **Start from the docs root** (e.g., `docs.yoursite.com`)
2. **Set appropriate depth** — Most docs need 3-5 levels
3. **Exclude irrelevant paths** — Changelog, release notes (unless needed)
4. **Re-sync regularly** — Set up scheduled syncs for updated content

<Tip>
  Use the **auto-detect feature** during onboarding. Ansa automatically discovers docs pages at `/docs`, `/documentation`, `/help`, `/guides`, and `/api`.
</Tip>

### Structuring Content for Best Results

Good documentation indexing:

✅ Clear headings and subheadings
✅ Concise paragraphs
✅ Code examples with context
✅ Descriptive link text

Avoid:
❌ Single-page docs with everything
❌ Heavily nested accordions (may not crawl)
❌ Content loaded via JavaScript (use static/SSR)

## Agent Configuration

### System Prompt for Documentation

```
You are a helpful documentation assistant for [Product Name].

Your role:
- Answer questions accurately based on the documentation
- Provide code examples when relevant
- Link to relevant documentation pages for further reading
- Be concise but thorough

When you don't know the answer:
- Acknowledge honestly that you couldn't find this in the docs
- Suggest related topics that might help
- Offer to connect them with support if needed

Format responses for readability:
- Use markdown formatting
- Include code blocks with proper syntax highlighting
- Use bullet points for lists
```

### Temperature Settings

| Use Case             | Temperature | Why                                 |
| -------------------- | ----------- | ----------------------------------- |
| **API Reference**    | 0.1 - 0.3   | Accuracy is critical                |
| **Tutorials/Guides** | 0.3 - 0.5   | Balance of accuracy and explanation |
| **Conceptual Docs**  | 0.5 - 0.7   | More natural explanations           |

### Model Selection

For documentation assistants:

| Model                 | Best For                                  |
| --------------------- | ----------------------------------------- |
| **Claude 3.5 Sonnet** | Excellent at explaining code and concepts |
| **GPT-4o**            | Great for technical documentation         |
| **GPT-4o-mini**       | Cost-effective for high-volume sites      |

## Widget Configuration

### Suggested Messages

Guide users to common topics:

<Screenshot src="/screenshots/widget.png" alt="Widget customization" />

Configure suggested messages for quick access:

```json theme={null}
{
  "suggestedMessages": [
    "How do I get started?",
    "Show me authentication examples",
    "What are the API rate limits?",
    "How do I handle errors?"
  ]
}
```

### Placement

For documentation sites:

| Placement        | Position    | When                   |
| ---------------- | ----------- | ---------------------- |
| **Bottom Right** | Default     | General docs sites     |
| **Bottom Left**  | Alternative | If conflicts with ToC  |
| **Inline**       | Embedded    | Specific help sections |

## Triggers for Documentation

### Engagement on Complex Pages

Help users on lengthy or complex docs:

```json theme={null}
{
  "name": "Long Page Help",
  "triggerType": "time_on_page",
  "conditions": {
    "timeOnPage": 60,
    "page": "/docs/advanced/*"
  },
  "actionType": "show_bubble",
  "actionConfig": {
    "message": "Need help understanding this? I can explain any part.",
    "duration": 8
  }
}
```

### Search Page Fallback

Engage users who might not find what they need:

```json theme={null}
{
  "name": "Search Assistance",
  "triggerType": "time_on_page",
  "conditions": {
    "timeOnPage": 30,
    "page": "/docs/search*"
  },
  "actionType": "open_chat",
  "actionConfig": {
    "message": "Can't find what you're looking for? Tell me what you need and I'll help you find it."
  }
}
```

## Handling Unknown Questions

When the agent can't find an answer in the docs:

### 1. Honest Acknowledgment

System prompt should include:

```
When information isn't in the documentation:
- Say "I couldn't find this in our documentation"
- Suggest similar topics that might help
- Offer to connect them with support
```

### 2. Fallback Form

Create a form for questions that need human help:

```json theme={null}
{
  "name": "docs_feedback",
  "description": "Use when you cannot answer the user's question from the documentation.",
  "executionType": "form",
  "formSchema": {
    "fields": [
      {
        "name": "question",
        "label": "Your Question",
        "type": "textarea",
        "defaultValue": "{{context.lastMessage}}"
      },
      {
        "name": "email",
        "label": "Email (for follow-up)",
        "type": "email"
      }
    ],
    "submitLabel": "Submit Question",
    "successMessage": "We'll add this to our docs or get back to you!"
  },
  "formPostActions": [
    {
      "type": "slack",
      "webhookUrl": "https://hooks.slack.com/...",
      "messageTemplate": "📝 *Docs Gap Identified*\n\n{{question}}\n\nFrom: {{email}}"
    }
  ]
}
```

## Identifying Documentation Gaps

### Review Low-Confidence Conversations

Use the analytics dashboard to find:

* Questions with low confidence scores
* Repeated questions not well-answered
* Topics users ask about that aren't documented

<Screenshot src="/screenshots/analytics.png" alt="Analytics" />

### Create Q\&A Pairs

For frequently asked questions not well-covered:

<Screenshot src="/screenshots/qa-sources.png" alt="Q&A sources" />

1. Go to **Knowledge Base → Q\&A**
2. Add the exact question users ask
3. Provide the ideal answer
4. These get high priority in searches

## Integration with Doc Platforms

### GitBook, Docusaurus, Mintlify

Web crawl your public docs URL. Ensure:

* Content is server-rendered
* No robots.txt blocking
* Sitemap available for best coverage

### Notion, Confluence

For internal docs:

1. Export as PDF or markdown
2. Upload via file sources
3. Set up periodic re-uploads for updates

### API Reference (OpenAPI)

Upload your OpenAPI/Swagger spec as a file source. The agent will understand:

* Endpoints and methods
* Request/response schemas
* Authentication requirements

## See Also

* [Knowledge Base](/agents/knowledge-base) — Source types and configuration
* [Widget Customization](/widget/customization) — Suggested messages, themes
* [Confidence Scores](/user-guides/confidence-scores) — Understanding answer quality
* [Q\&A Sources](/agents/knowledge-base#qa-pairs) — Adding vetted answers