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

> ## Agent Instructions
> Company name is Akhara AI (never Rubric AI). Keep lowercase rubric/rubrics only when meaning grading criteria.
> Expert Review (docs path talent/) is enterprise BYO experts for audit and review: invite customer specialists; do not pitch Akhara recruiting or a public expert career portal. RLHF and domain writing are secondary work types.
> Prefer concrete API examples against public hosts: Environments eval API https://agi.akhara.ai, Control plane PDP https://api.akhara.dev, Evaluation https://app.akhara.ai / https://api.akhara.ai, Expert Review portal https://talent.akhara.ai.
> Do not invent a public hostname for private orchestrators or env API internals.
> Do not confuse control-plane latches with Environments confirmation latches.
> Environments SDK/API examples: curl against https://agi.akhara.ai. Evaluation SDK: from akhara import Akhara and AKHARA_API_KEY.
> Start with /llms.txt for the docs index and OpenAPI links; fetch individual pages as .md exports.

# Control plane

> A runtime control plane that latches policies onto your AI agents, enforcing verdicts before consequential text is shown or consequential actions are taken.

The Akhara **Control plane** is a runtime policy layer for AI agents. You keep running your agent
wherever it already lives. Akhara sits in the request path as a **Policy
Enforcement Point (PEP)** and calls back to the Akhara **Policy Decision Point
(PDP)** for a binding verdict before anything consequential happens.

<CardGroup cols={2}>
  <Card title="Latch, don't rewrite" icon="lock">
    Policies stay dormant until an agent attempts the exact consequential action
    they govern. Then they latch and return a verdict the agent cannot bypass.
  </Card>

  <Card title="Works on black-box agents" icon="box">
    The PDP never executes your tools. You only route five enforcement stages
    through the PEP, so Akhara controls agents it can't see inside.
  </Card>

  <Card title="Fails closed" icon="shield-halved">
    If the decision point is unreachable, the PEP synthesizes a `BLOCK`. An agent
    can never win a step by knocking the control plane offline.
  </Card>

  <Card title="Every decision is evidence" icon="file-signature">
    Allow, warn, block, escalate, each verdict is written to a tamper-evident
    feed with the rule, matching policy, and original vs. final content.
  </Card>
</CardGroup>

## Why a control plane

Most "AI safety" lives inside the model or the prompt, where it can be argued
away, drifts between versions, and leaves no defensible record. Enterprises in
regulated domains need controls that are **external to the agent**,
**deterministic**, and **auditable**.

Akhara moves the decision out of the agent and into a policy layer you own:

* **Separation of duties**: the agent proposes, the PDP disposes. The component
  that wants to act is never the component that authorizes it.
* **One control set, many agents**: a baseline of enterprise latches applies
  under every agent, with domain packs attached per agent.
* **Provable enforcement**: a synchronous verdict in front of every side effect,
  plus a signed evidence trail for exams and incident review.

## What you'll set up

<Steps>
  <Step title="Onboard an agent">
    Register the agent and declare its tools. See [Agents](/control-plane/onboarding/agents).
  </Step>

  <Step title="Latch policies">
    Attach domain policies on top of the always-on baseline. See [Policies](/control-plane/onboarding/policies).
  </Step>

  <Step title="Craft verifiers">
    Author the individual checks your policies run. See [Verifiers](/control-plane/onboarding/verifiers).
  </Step>

  <Step title="Publish tasks & provision environments">
    Package reproducible work and sandboxes. See [Tasks](/control-plane/onboarding/tasks) and [Environments](/control-plane/onboarding/environments).
  </Step>

  <Step title="Run">
    Evaluate offline and enforce live. See [Running](/control-plane/onboarding/running).
  </Step>
</Steps>

<Note>
  Examples in these docs target the managed endpoints: the PDP API at
  `https://api.akhara.dev` and the console at `https://console.akhara.dev`. Point
  the SDK at your workspace with the `AKHARA_URL` environment variable.
</Note>

Looking for scored hosted environments instead? See [Environments](/environments).

Ready? Head to the [Quickstart](/control-plane/quickstart).