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

# AI Tools

> Resources for building with AI assistants — skills, agent references, and LLM-optimized docs

Bota provides a set of resources designed for AI-assisted development. Whether you're using Claude, Cursor, GitHub Copilot, or any other AI coding assistant, these tools help the model understand the Bota API accurately.

## LLM Reference Docs

Two machine-readable files are available at well-known URLs, following the [llmstxt.org](https://llmstxt.org) standard:

<CardGroup cols={2}>
  <Card title="llms.txt" icon="list" href="https://docs.bota.dev/llms.txt">
    Link index — one line per doc page. Use when you want an agent to discover and fetch individual pages.
  </Card>

  <Card title="llms-full.txt" icon="file-lines" href="https://docs.bota.dev/llms-full.txt">
    Full reference — the entire API in one document, with canonical flows, gotchas, and code examples. Fetch once and the agent knows the full API.
  </Card>
</CardGroup>

**How to use in Cursor or Claude Code:**

```
@https://docs.bota.dev/llms-full.txt

How do I set up streaming upload for a 4G device?
```

## Skills

Skills are self-contained integration guides — one per common task — with working code, step-by-step instructions, and a gotchas section. Drop one into your AI assistant's context and it can implement the integration without hallucinating.

<CardGroup cols={2}>
  <Card title="Device Registration" icon="microchip" href="https://github.com/bota-dev/bota-skills/blob/main/device-registration/skill.md">
    Register a device, bind to an end user, handle reassignment and lifecycle
  </Card>

  <Card title="Recording Upload" icon="upload" href="https://github.com/bota-dev/bota-skills/blob/main/recording-upload/skill.md">
    Create a recording, get a presigned URL, upload to S3, complete
  </Card>

  <Card title="Webhook Handling" icon="webhook" href="https://github.com/bota-dev/bota-skills/blob/main/webhook-handling/skill.md">
    Register an endpoint, verify HMAC-SHA256 signatures, handle retries
  </Card>

  <Card title="Auto-Processing" icon="bolt" href="https://github.com/bota-dev/bota-skills/blob/main/auto-processing/skill.md">
    Enable zero-code transcription and summary pipeline
  </Card>

  <Card title="Streaming Upload" icon="signal-stream" href="https://github.com/bota-dev/bota-skills/blob/main/streaming-upload/skill.md">
    Upload audio chunks during recording for faster time-to-transcript
  </Card>
</CardGroup>

**How to use:**

```
@https://raw.githubusercontent.com/bota-dev/bota-skills/main/recording-upload/skill.md

Implement recording upload in my Express backend
```

All skills are open source in [github.com/bota-dev/bota-skills](https://github.com/bota-dev/bota-skills).

## MCP Server

The Bota MCP server connects your AI assistant directly to your Bota project — list devices, inspect recordings, trigger test webhooks, and more without leaving your IDE. You can also issue scoped tokens so end users can query their own recordings with an AI assistant.

<Card title="MCP Server" icon="server" href="/mcp-server">
  Developer tier (full project access) and end user tier (scoped to their recordings)
</Card>