Skip to main content
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.

Latch, don't rewrite

Policies stay dormant until an agent attempts the exact consequential action they govern. Then they latch and return a verdict the agent cannot bypass.

Works on black-box agents

The PDP never executes your tools. You only route five enforcement stages through the PEP, so Akhara controls agents it can’t see inside.

Fails closed

If the decision point is unreachable, the PEP synthesizes a BLOCK. An agent can never win a step by knocking the control plane offline.

Every decision is evidence

Allow, warn, block, escalate, each verdict is written to a tamper-evident feed with the rule, matching policy, and original vs. final content.

​
The runtime loop

Every consequential step follows the same loop. The agent proposes, the PEP intercepts, the PDP decides, and the decision leaves a signed trace: Interception is selective: a latch only bites on the consequential action it governs, so routine calls pass straight through. See Tool-call interception for the wrap pattern and exactly what context crosses to the PDP, and Audit and evidence for how each verdict becomes a tamper-evident record.

​
From policy to enforcement

Enterprise policies do not stay prose. They are crafted into machine-checkable verifiers, bundled into policy packs, and latched onto the specific actions they govern: The crafting workflow lives in Policies and Verifiers.

​
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

1

Onboard an agent

Register the agent and declare its tools. See Agents.
2

Latch policies

Attach domain policies on top of the always-on baseline. See Policies.
3

Craft verifiers

Author the individual checks your policies run. See Verifiers.
4

Publish tasks & provision environments

Package reproducible work and sandboxes. See Tasks and Environments.
5

Run

Evaluate offline and enforce live. See Running.
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.
Looking for a domain walk-through instead of mechanisms? The cookbooks show the same machinery applied to healthcare, finance, and insurance. Looking for scored hosted environments instead? See Environments. Ready? Head to the Quickstart.