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

# Choose your AtlaSent quickstart

> Pick the shortest safe path for developers, enterprise operators, or AI-agent integrations.

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

<CardGroup cols={3}>
  <Card title="Developer / API" icon="code" href="/quickstart/developer-api">
    Evaluate a sandbox action, interpret the decision, handle a bounded Permit, verify it, and inspect evidence.
  </Card>

  <Card title="Enterprise operator" icon="building" href="/quickstart/enterprise-operator">
    Choose a protected action, connect the minimum evidence, run a rehearsal, and understand production-readiness boundaries.
  </Card>

  <Card title="AI agent / MCP" icon="robot" href="/quickstart/agent-mcp">
    Put AtlaSent between an agent tool request and a consequential effect without treating tool access as organizational authority.
  </Card>
</CardGroup>

## 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.

<Note>
  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.
</Note>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.