Skip to main content
AtlaSent authorizes consequential computational actions at execution time. Start with the path that matches how you will use it.

Developer / API

Evaluate a sandbox action, interpret the decision, handle a bounded Permit, verify it, and inspect evidence.

Enterprise operator

Choose a protected action, connect the minimum evidence, run a rehearsal, and understand production-readiness boundaries.

AI agent / MCP

Put AtlaSent between an agent tool request and a consequential effect without treating tool access as organizational authority.

​
One lifecycle

All three paths use the same lifecycle: Verified identity → organizational authority → authorization → Permit → verification → execution → evidence Do not collapse the stages. An allow does not prove execution. Permit verification does not prove the downstream effect occurred.
The Developer / API quickstart uses a demo action that executes nothing. Console keys are live keys, so its requests send context.environment: "production"; that names the key’s environment and activates nothing. The other paths have their own safety guidance: follow the page you choose. Protecting a real production action is a separate, controlled step.