Make Your App Agent-Ready in 5 Minutes

ACL helps existing app capabilities (APIs, MCP tools, Zapier actions, CLIs) become safer for AI agents to use. You define the allowed actions and checks, ACL runs the workflow, and every run produces a receipt.

Recommended path: /agenticflow to learn the pattern, then /playground to prototype your own contracts.
LLM intent / slots ACL Contract rules + checks Tools / APIs apps / Zapier / MCP Receipts • Checks • Preview / Confirm what ran, what changed, what passed, what failed
APIs give access. ACL gives control.

1. Understand the Pattern

Use the guided tutorial in /agenticflow. Run a request, inspect the generated ACL, then open the receipt summary and full JSON proof.

2. Prototype a Contract

Use the playground to load a template, modify the steps, and run it directly. Start with read flows, then try preview/confirm patterns for writes.

3. Wrap App Capabilities

Expose a few actions as tools (API wrappers, MCP, Zapier, or CLI), then define one or two ACL flows around them with checks and receipts.

Quick Commands

Run locally and iterate quickly:

go run ./cmd/acl serve
acl run examples/your_flow.acl
acl check examples/your_flow.acl

Production recommendation: use the LLM to extract structured intent (JSON), compile to ACL templates, and keep freeform ACL generation as fallback for novel requests.