How it works

How the Akhara products work together: author verifiers and rubrics at build time, gate changes in CI, verify at runtime, and feed production back into evals.

Akhara is one lifecycle across four products. You author checks before you build, gate every agent change in CI, enforce policy while the agent runs, and feed what production teaches you back into the checks. This page walks the loop end to end and shows which artifacts move between products.

The lifecycle

Stage	Product	Key artifacts
Build	Evaluation, Environments, Control plane, Expert Review	Datasets, rubrics, tasks, verifiers, policies
Gate	Evaluation, Environments	Scores, terminal rewards, pass/fail gates
Run	Control plane	Verdicts, permits, signed evidence
Learn	Expert Review, Evaluation	Audited trajectories, updated rubrics and tasks

Build: author the checks

Everything downstream runs on artifacts you author from your own policies, regulations, and domain knowledge:

• Datasets and rubrics in Evaluation define what good looks like before you build. See datasets and rubrics.
• Tasks and verifiers in Environments turn those definitions into scored, simulated episodes. Each environment bundles an app, backend, task definitions, and verifiers that score session and device state.
• Policies in the control plane encode which actions are consequential and what must hold before they execute, including latches that activate only on the action they govern. See policy authoring and verifier crafting.
• Domain writing from Expert Review: your invited specialists author scenarios and success criteria in their specialty, which feed the Environments task banks. See domain writing.

Artifacts are versioned, so a CI result and a runtime verdict can both point at the exact revision that produced them. See evaluation versioning.

Gate: every change runs the suite

Before an agent change ships, it clears two kinds of pre-deployment checks:

1. Eval suites run against the Evaluation API and a threshold check fails the pipeline when scores regress. See CI/CD quality gates.
2. Simulation runs in Environments score multi-step behavior in realistic, stateful apps: you call the eval API at https://agi.akhara.ai, and each episode returns a terminal reward of +1, 0, or -1 plus a full trajectory. See scores and stats.

A change that clears both gates is promoted. The same policies you tested against are the ones the gateway enforces once the agent is live, so there is no gap between what CI measured and what production allows.

Run: the gateway verifies every step

At runtime, your agent passes through the Akhara gateway on every step. The PEP (an SDK in your runtime) intercepts inputs, model output, deliveries, and consequential tool calls, and asks the PDP at https://api.akhara.dev for a verdict: ALLOW, WARN, BLOCK, or ESCALATE. On ALLOW for a consequential action, the PDP mints a one-time permit; downstream services should refuse to execute without one. The PDP decides and never executes tools itself, and enforcement is fail-closed by default.

Every verdict is written to an append-only evidence feed. You can seal a decision and later verify it, so audit does not depend on trusting the logs. See the control plane architecture for the full request lifecycle.

Learn: production feeds the next iteration

The evidence trail and captured trajectories close the loop:

• Your org-invited specialists in Expert Review review agent runs: trajectories, scores, failures, and policy-sensitive cases the automated checks flagged or missed.
• Their findings tighten rubrics, tasks, and policies, which flow back into the build-time artifacts.
• The next CI run gates against the updated suites, so a regression that production surfaced is caught before it ships again.

What moves between products

Artifact	Produced by	Consumed by
Datasets and rubrics	Evaluation, with expert input	CI gates, expert review
Tasks and verifiers	Environments, with domain writing	Simulation runs in CI
Policies and latches	Control plane authoring	PDP verdicts at runtime
Trajectories and scores	Environments and gateway runs	Evaluation, Expert Review
Signed evidence	Control plane at runtime	Audit, Expert Review

For per-term definitions across the suite, see the glossary.