> ## 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. # Glossary > Cross-product terms for the Akhara AI verification suite: control plane, Environments, Evaluation, and Expert Review. Short definitions for engineers reading across the Akhara AI suite. Each product also has deeper concept pages; use those when you need mechanics, not just vocabulary. For Evaluation metric definitions, see the [AI / ML metrics](/evaluation/docs/glossary-appendix/ai-ml-metrics) glossary. ## Suite | Term | Definition | | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Verification layer** | What Akhara AI is as a whole: measurable checks before ship, runtime policy after, and evidence you can audit. Not a single model, harness, or chat proxy. See [Akhara AI](/). | | **Quality gate** | A threshold check (usually in CI via Evaluation) that fails the pipeline when scores regress. Design-time and pre-deploy measurability. | | **Runtime policy** | Control-plane enforcement at consequential agent steps (PEP/PDP verdicts, latches, permits). Different job from quality gates: gates score and block deploys; runtime policy blocks or allows live actions. See [Control plane](/control-plane). | | **Runtime verification gateway** | Where agent steps pass through verification and a decision (Allow, Warn, Block, Escalate) before the next step continues. Observability reconstructs later; Akhara verifies at the runtime boundary. See [Akhara AI](/#verification-at-the-runtime-boundary). | ## Control plane Runtime policy for AI agents. Start with [concepts overview](/control-plane/concepts/overview). | Term | Definition | | ------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **PDP** | Policy Decision Point. The service that **decides** (`https://api.akhara.dev`). It evaluates policies and returns a verdict. It never executes your tools. See [Overview](/control-plane/concepts/overview). | | **PEP** | Policy Enforcement Point. The SDK you embed in the agent runtime. It **enforces**: for each risky step it calls the PDP and applies the verdict before the side effect. See [Overview](/control-plane/concepts/overview). | | **Latch** | A control-plane policy that activates only on the consequential action it governs (for example, renew a prescription), not on earlier chat. Do not confuse with Environments [confirmation latches](/environments/mechanics/confirmation-latches). See [Latching](/control-plane/concepts/latching). | | **Permit / permitId** | One-time authorization id the PDP mints on `ALLOW` for an `action` stage. Downstream services should refuse to execute without a valid permit. See [Overview](/control-plane/concepts/overview). | | **Verdict** | PDP decision for a step: `ALLOW`, `WARN`, `BLOCK`, or `ESCALATE`. See [Verdicts](/control-plane/concepts/verdicts). | | **ALLOW** | Proceed; for `action` stages the PDP may mint a `permitId`. | | **WARN** | Proceed with a recorded warning (policy-dependent handling in your runtime). | | **BLOCK** | Do not execute the step. | | **ESCALATE** | Hold for human or higher-authority review before proceeding. | | **Fail-closed** | If the PDP is unavailable or the decision path is undecided, the PEP does not silently permit. See [Fail-closed](/control-plane/concepts/fail-closed). | | **Evidence / signed evidence trail** | Sealed decision records you can sign and later verify for audit. See [Sign a record](/control-plane/api-reference/endpoint/sign-record) and [Verify a record](/control-plane/api-reference/endpoint/verify-record). | ## Environments Environment-as-a-Service for scoring agents on hosted apps. Start with [Environments](/environments). | Term | Definition | | -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Environment / env\_id** | One deployable unit: app + backend + tasks + verifiers, addressed by `env_id`. See [Environment](/environments/mechanics/environment). | | **Eval API** | Public evaluation API at `https://agi.akhara.ai` (for example `POST /evaluations/run`). See [Evaluations API](/environments/api/evaluations). | | **Admin** | Admin UI and APIs at `https://admin-agi.akhara.ai`. See [Dashboard API](/environments/api/dashboard). | | **Orchestrator / env API** | Private env protocol (`/v1/env/*`, `/tasks`). Not publicly routed; do not invent a public hostname for it. See [Env API](/environments/api/env-api). | | **VU-\*** | Session success-criteria verifiers (names often prefixed `VU-`). They score whether the episode met task goals. See [Verifiers](/environments/mechanics/verifiers). | | **Terminal reward** | Episode outcome score restricted to `+1`, `0`, or `-1`. See [Scores and stats](/environments/results/scores-and-stats). | | **Confirmation latch** | Sticky `confirmation_violation` when the agent skips a required `needs_confirmation` before an irreversible action. Environments-only; not a control-plane latch. See [Confirmation latches](/environments/mechanics/confirmation-latches). | ## Evaluation Domain-agnostic scoring of models and agents. Start with [Introduction](/evaluation/docs/introduction). | Term | Definition | | ---------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Rubric** | Grading criteria or scale for human or automated review. A domain term, not the company name (company is Akhara AI). See [Rubrics](/evaluation/api-reference/rubrics/overview). | | **Dataset** | Curated collection of samples used as the unit of eval input. See [Datasets](/evaluation/api-reference/datasets/overview). | | **Sample** | One evaluable item inside a dataset (prompt, context, expected output, metadata). See [Samples](/evaluation/api-reference/samples/overview). | | **Evaluation** | A scored run of a model or agent against a dataset (and rubrics / reviewers as configured). See [Evaluations](/evaluation/api-reference/evaluations/overview). | | **CI gate** | Scripted or hosted threshold check that fails CI when evaluation scores regress. See [CI/CD](/evaluation/docs/tutorials/ci-cd). | | **Quality gate** | Same idea as CI gate in the Evaluation product: measurable pass/fail before promote. Distinct from control-plane runtime policy. | ## Expert Review Enterprise-invited expert **audit and review**: specialists review agent runs, scores, failures, task quality, and policy-sensitive cases. Docs path `talent/`. Start with [Expert Review introduction](/talent/introduction). | Term | Definition | | -------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **BYO / enterprise-invited experts** | Your organization's specialists, invited to audit runs, review hard cases, and improve tasks and rubrics. Portal: [`talent.akhara.ai`](https://talent.akhara.ai). | | **Expert audit / review** | Domain specialists reviewing trajectories, scores, failures, and task or rubric quality when automated scores are not enough. Primary Expert Review role in the verification stack. Distinct from Evaluation's human-review scoring features. | | **RLHF evaluations** | Secondary capability: preference, ranking, safety-flag, and rationale work that feeds Evaluation. See [RLHF evaluations](/talent/guidance/rlhf-evaluations). | | **Domain writing for RL environments** | Secondary capability: scenario and success-criteria authoring in the expert's specialty, feeding Environments task banks. See [Domain writing](/talent/guidance/domain-writing). |