> ## Documentation Index
> Fetch the complete documentation index at: https://docs-staging-actions-triggers-prototype.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

> Learn how to leverage Auth0 for AI Agents to secure every layer of your GenAI stack.

# Auth0 for AI Agents

Generative AI (GenAI) applications powered by large language models (LLMs) and AI agents are changing how users interact with software. As developers integrate AI capabilities that handle login, data access, and tool execution into their applications, securing these interactions becomes critical.

Auth0 for AI Agents leverages Auth0’s robust identity and access management (IAM) platform to secure every layer of your GenAI stack. It provides comprehensive, enterprise-grade security for:

* **Human users:** Ensure only authorized individuals can interact with AI models and applications.
* **AI agents:** Control autonomous AI agent access to external APIs using <Tooltip tip="OAuth 2.0: Authorization framework that defines authorization protocols and workflows." cta="View Glossary" href="/docs/glossary?term=OAuth+2.0">OAuth 2.0</Tooltip> scopes.
* **External APIs and tools:** Securely connect AI agents to Google, Slack, GitHub, and more. Auth0 automatically refreshes and exchanges tokens without user intervention.
* **Sensitive data:** Enforce granular, least-privilege permissions to protect sensitive data from unauthorized AI agent access.

To start building with Auth0 for AI Agents, read the [Auth0 for AI Agents documentation](https://auth0.com/ai/docs).

## Use cases

Auth0 for AI Agents empowers developers to build and deploy secure AI-powered applications with:

* **Seamless integrations:** Integrates out-of-the-box with popular AI frameworks like LangChain, LlamaIndex, and the Vercel AI SDK.
* **Comprehensive security controls:** Secures authentication flows with OAuth 2.0 and <Tooltip tip="OpenID: Open standard for authentication that allows applications to verify users' identities without collecting and storing login information." cta="View Glossary" href="/docs/glossary?term=OpenID">OpenID</Tooltip> Connect and manages access for both human users and AI agents.
* **Asynchronous authorization:** Enables human-in-the-loop controls for critical actions.
* **<Tooltip tip="Fine-grained Authorization (FGA): Auth0 product allowing individual users access to specific objects or resources." cta="View Glossary" href="/docs/glossary?term=Fine-grained+authorization">Fine-grained authorization</Tooltip> for RAG:** Enforces granular access control within Retrieval Augmented Generation (RAG) pipelines.

### User authentication

Leverage OAuth 2.0 and OpenID Connect to securely authenticate users with [Universal Login](/docs/authenticate/login/auth0-universal-login). With [Client-Initiated Account Linking](https://auth0.com/ai/docs/client-initiated-account-linking), AI agents can request access and connect to multiple <Tooltip tip="Identity Provider (IdP): Service that stores and manages digital identities." cta="View Glossary" href="/docs/glossary?term=identity+providers">identity providers</Tooltip> on the user’s behalf through Auth0.

### Call APIs on users’ behalf

Using [Token Vault](/docs/secure/tokens/token-vault), AI agents can fetch <Tooltip tip="Access Token: Authorization credential, in the form of an opaque string or JWT, used to access an API." cta="View Glossary" href="/docs/glossary?term=access+tokens">access tokens</Tooltip> for external identity providers to call their APIs, all through a single Auth0 integration. For example, you can use Token Vault to:

1. Authenticate a user with an external identity provider like Google.
2. Use OAuth scopes to authorize access to the Google Calendar API.
3. Get an access token to call the Google Calendar API to schedule a meeting.

Auth0 for AI Agents supports the following social, enterprise, and custom identity providers:

* Google
* Microsoft
* Box
* Slack
* GitHub
* OpenID Connect
* Custom connection

### Asynchronous authorization

Add human-in-the-loop controls for critical or delayed actions using secure protocols, such as:

* [Client-Initiated Backchannel Authentication (CIBA)](/docs/get-started/authentication-and-authorization-flow/client-initiated-backchannel-authentication-flow): Enables AI agents to asynchronously implement secure backchannel authentication and <Tooltip tip="Authorization Flow: Authorization grant (or workflow) specified in the OAuth 2.0 framework." cta="View Glossary" href="/docs/glossary?term=authorization+flows">authorization flows</Tooltip> when user approval is required before taking an action.
* [Rich Authorization Requests (RAR)](/docs/get-started/authentication-and-authorization-flow/authorization-code-flow/authorization-code-flow-with-rar): Enhance security by requesting specific authorization permissions for users to approve through push notifications.

### Authorization for RAG

Use [Auth0 FGA](https://docs.fga.dev/) to enforce document and relationship-level access control in your Retrieval Augmented Generation (RAG) pipelines:

* Document-level access control: Performs granular permission checks on RAG data sources.
* Relationship-Based Access Control (ReBAC): Replaces broad roles with precise, fine-grained relationship-based access control decisions.
* Compliance support: Ensures only authorized data is retrieved for data privacy and regulatory compliance.

## AI Framework Integrations

Auth0 for AI Agents integrates out-of-the-box with leading [GenAI frameworks and tools](https://auth0.com/ai/docs/sdks), such as:

* LangChain
* LlamaIndex
* Vercel AI SDK
* GenKit
* Cloudflare Agents
* [Cloudflare Model Context Protocol (MCP) Servers](https://auth0.com/ai/docs/cloudflare-mcp)

## Next steps

Ready to start building? Explore our [quickstarts](https://auth0.com/ai/docs/get-started), [how-tos](https://auth0.com/ai/docs/how-tos), and [SDKs](https://auth0.com/ai/docs/sdks) in the Auth0 for AI Agents documentation.