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

> ## Agent Instructions
> These docs moved from docs.flintai.dev to docs.switchagents.ai. Use docs.switchagents.ai for every link and request.
> To search these docs from an AI tool, connect the MCP server at https://docs.switchagents.ai/mcp. The page index is at https://docs.switchagents.ai/llms.txt.

# Switch AI products

> Discover, prove, and protect your AI agents

<CardGroup cols={3}>
  <Card title="Switch Rooms" icon="comments" href="/switch-rooms/index">
    Bring humans and AI agents together in the tools where your team already works. Shared context, and rules for who can address each agent.
  </Card>

  <Card title="Switch Trust" icon="shield-check" href="/switch-trust/index">
    Discover AI agents in your code, monitor runtime sessions, and enforce guardrails. Full stack AgentOps.
  </Card>

  <Card title="Switch Trust CLI" icon="terminal" href="/switch-trust-cli/index">
    Static code analysis and runtime evaluation for AI agents. Fast local scanning and testing.
  </Card>
</CardGroup>

## Make AI earn it

Ship AI agents with confidence.

<Card title="Flint AI on GitHub" icon="github" href="https://github.com/sandbox-quantum/flintai-cli">
  Source code, example agents, and issue tracking
</Card>

Trust in AI agents should be earned, not assumed. Switch Trust helps you verify agent reliability before production.

## Switch AI family

| | **Switch Trust** | **Switch Trust CLI** | **Switch Rooms** |
| - | - | - | - |
| **What** | Full stack AgentOps platform | Command-line scanner and evaluator | Rooms where a team and its agents work together |
| **Where** | Cloud-based (GitHub integration + SDK) | Local, on your machine | Your team's messaging app, on a server you run |
| **Best for** | Teams managing agents in production | Developers testing agents locally | Teams whose agents each hold one slice of the work |
| **Setup** | GitHub Action + SDK wrapper | `pip install flintai-cli` | Switch Console, the desktop app that sets the rest up |
| **Get started** | [Discover quickstart →](/switch-trust/getting-started/discover) | [Scan quickstart →](/switch-trust-cli/scan/getting-started) | [Setting up Switch →](/switch-rooms/getting-started/index) |

### Works with your agent framework

Flint AI Scan recognizes these frameworks in your code:

<div className="framework-pills">
  <div className="framework-pill"><img src="https://mintcdn.com/sandboxaq/ZJtJHzDjxXqPUlNg/images/frameworks/google.svg?fit=max&auto=format&n=ZJtJHzDjxXqPUlNg&q=85&s=e44a4103989b26059713991ed143ce28" alt="" noZoom width="20" height="20" data-path="images/frameworks/google.svg" /><span>Google ADK</span></div>
  <div className="framework-pill"><img src="https://mintcdn.com/sandboxaq/ZJtJHzDjxXqPUlNg/images/frameworks/gemini.svg?fit=max&auto=format&n=ZJtJHzDjxXqPUlNg&q=85&s=75da70c3b445a9c4263aa756d6b49beb" alt="" noZoom width="20" height="20" data-path="images/frameworks/gemini.svg" /><span>Google GenAI</span></div>
  <div className="framework-pill"><img src="https://mintcdn.com/sandboxaq/2_u5qeh8JPl_KDDW/images/frameworks/anthropic.svg?fit=max&auto=format&n=2_u5qeh8JPl_KDDW&q=85&s=bfe34183e179050fbfc771fabf6dd8db" alt="" noZoom width="20" height="20" data-path="images/frameworks/anthropic.svg" /><span>Anthropic</span></div>
  <div className="framework-pill"><img src="https://mintcdn.com/sandboxaq/2_u5qeh8JPl_KDDW/images/frameworks/openai.svg?fit=max&auto=format&n=2_u5qeh8JPl_KDDW&q=85&s=8f7719f2c3e264dc126057a5b416d300" alt="" noZoom width="20" height="20" data-path="images/frameworks/openai.svg" /><span>OpenAI</span></div>
  <div className="framework-pill"><img src="https://mintcdn.com/sandboxaq/2_u5qeh8JPl_KDDW/images/frameworks/openai.svg?fit=max&auto=format&n=2_u5qeh8JPl_KDDW&q=85&s=8f7719f2c3e264dc126057a5b416d300" alt="" noZoom width="20" height="20" data-path="images/frameworks/openai.svg" /><span>OpenAI Agents SDK</span></div>
  <div className="framework-pill"><img src="https://mintcdn.com/sandboxaq/2_u5qeh8JPl_KDDW/images/frameworks/langchain.svg?fit=max&auto=format&n=2_u5qeh8JPl_KDDW&q=85&s=463e80393b48bd882996cf2e54c6ae61" alt="" noZoom width="20" height="20" data-path="images/frameworks/langchain.svg" /><span>LangGraph</span></div>
  <div className="framework-pill"><img src="https://mintcdn.com/sandboxaq/2_u5qeh8JPl_KDDW/images/frameworks/crewai.svg?fit=max&auto=format&n=2_u5qeh8JPl_KDDW&q=85&s=9c80843734146b9fe7ff1eac214c5ea8" alt="" noZoom width="20" height="20" data-path="images/frameworks/crewai.svg" /><span>CrewAI</span></div>
  <div className="framework-pill"><img src="https://mintcdn.com/sandboxaq/2_u5qeh8JPl_KDDW/images/frameworks/autogen.svg?fit=max&auto=format&n=2_u5qeh8JPl_KDDW&q=85&s=37f5754191f37a904ac87b870acb4a97" alt="" noZoom width="20" height="20" data-path="images/frameworks/autogen.svg" /><span>AutoGen</span></div>
  <div className="framework-pill"><img src="https://mintcdn.com/sandboxaq/ZJtJHzDjxXqPUlNg/images/frameworks/huggingface.svg?fit=max&auto=format&n=ZJtJHzDjxXqPUlNg&q=85&s=99ffdb1fc9b0d4f4aee1bc2d4bffd30c" alt="" noZoom width="20" height="20" data-path="images/frameworks/huggingface.svg" /><span>HuggingFace Transformers</span></div>
  <div className="framework-pill"><img src="https://mintcdn.com/sandboxaq/ZJtJHzDjxXqPUlNg/images/frameworks/huggingface.svg?fit=max&auto=format&n=ZJtJHzDjxXqPUlNg&q=85&s=99ffdb1fc9b0d4f4aee1bc2d4bffd30c" alt="" noZoom width="20" height="20" data-path="images/frameworks/huggingface.svg" /><span>HuggingFace smolagents</span></div>
</div>

Flint AI Eval tests your running agent rather than your source. It ships adapters for common agent runtimes, plus a generic HTTP adapter for any endpoint that takes a JSON POST and returns the reply in a JSON field.

## Why Switch Trust?

Developers are shipping agents faster than they can test them. Agents ignore instructions, call the wrong tools, or fabricate answers. You need confidence before production.

* **Scan code** for security risks and misconfigurations
* **Run adversarial evaluations** to test behavior under attack
* **Monitor runtime sessions** to see what agents actually do
* **Enforce guardrails** to prevent issues before they ship