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

# How It Works

> How Anti AI fits into your stack.

Anti AI sits between your AI agents and the services they call. Agents authenticate with Anti AI to get a short-lived token, then use that token to call your APIs, databases, or third-party services.

```
Your AI Agent
     ↓  (client_id + client_secret + scope)
  Anti AI
     ↓  (signed JWT, expires in 10 min)
Your APIs / Stripe / GitHub / AWS / etc.
```

Add two lines of SDK code — Anti AI handles the rest.

## What it gives you

* **One identity per agent** — know exactly which agent did what, revoke one without touching others
* **Short-lived tokens** — agents get access only to what they need, right when they need it
* **Policies** — you decide what each agent is allowed to do; deny-by-default
* **Audit trail** — every action logged and tamper-proof

## Works with any framework

CrewAI, LangGraph, LangChain, AutoGen, Semantic Kernel, or any custom agent that can make HTTP requests.