Documentation

Everything you need to integrate Agent Access Control into your infrastructure.

What is Agent Access Control?

Agent Access Control is a deterministic security layer for AI agents. Unlike prompt-based restrictions, AAC uses mathematical policy evaluation to guarantee what agents can and cannot access.

• No LLM calls — Pure logic, no hallucinations
• Append-only audit trail — Every decision is logged
• Default deny — Secure by default
• Priority-based policies — First match wins

Core Concepts

Agents

AI systems that need controlled access to tools. Each agent has credentials and associated policies.

Tools & Actions

APIs or systems your agents call. Each tool has specific actions (e.g., read_customer, update_order).

Policies

Rules that allow or deny agent access. Evaluated by priority order, first match wins.

Gateway API

The single endpoint for all agent requests. Validates credentials, evaluates policies, and logs decisions.

Endpoint

POST https://agentaccesscontrol.com/api/gateway/execute

Headers

Authorization: Bearer aac_your_api_key_here
Content-Type: application/json

Request Body

{
  "tool": "customer_database",
  "action": "read_customer",
  "input": {
    "customer_id": "123"
  }
}

Success Response (Allow)

{
  "request_id": "550e8400-e29b-41d4-a716-446655440000",
  "decision": "allow",
  "policy_id": "abc123",
  "output": {
    "status": "simulated",
    "echo": { "customer_id": "123" }
  }
}

Deny Response

{
  "request_id": "550e8400-e29b-41d4-a716-446655440000",
  "decision": "deny",
  "policy_id": "xyz789",
  "error": {
    "code": "DENIED",
    "message": "Denied by policy: Deny Write Access"
  }
}

5-Minute Quickstart

1.Sign up and create your organization
2.Define your first agent (e.g., "Support Bot")
3.Add a tool with actions (e.g., "Customer DB" with read/write actions)
4.Create policies (allow read, deny write)
5.Generate API key and test with cURL

Security Model

✓API keys are SHA-256 hashed and never stored in plaintext
✓Row Level Security (RLS) enforces org-based isolation in Postgres
✓Audit logs are append-only and written before responses
✓Default deny policy — explicit allow required
✓No LLM calls means no prompt injection vectors