> ## 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.

# API overview

> Base URLs, environments, and which API to use.

## Production base URLs

| API                   | Base URL                      | Audience                         |
| --------------------- | ----------------------------- | -------------------------------- |
| Eval + dashboard API  | `https://agi.akhara.ai`       | Clients                          |
| Admin dashboard (SPA) | `https://admin-agi.akhara.ai` | Humans / ops                     |
| Env orchestrator      | Not publicly exposed          | Private network / operators only |

## Environments

Every evaluation targets an `env_id`:

| `env_id`             | Domain                    |
| -------------------- | ------------------------- |
| `amazon_gym_android` | Mobile shopping (Android) |
| `cvs_gym`            | Pharmacy retail           |

The control plane is shared; task banks, apps, and verifiers are environment-specific.

## Which API should I use?

| Goal                                  | Use                                                                      |
| ------------------------------------- | ------------------------------------------------------------------------ |
| Run a scored suite against my agent   | [Evaluations](/environments/api/evaluations): `POST /evaluations/run`    |
| Free-play without verifiers           | [Evaluations](/environments/api/evaluations#open-run): `POST /runs/open` |
| Pull trajectories / stats after a run | [Dashboard](/environments/api/dashboard)                                 |
| Drive reset/step yourself             | [Env API](/environments/api/env-api) (private network only)              |

## Conventions

* JSON request/response unless noted (export returns `application/zip`)
* Evaluation start returns **202** with `run_id`; poll status until `COMPLETED` / `FAILED` / `CANCELLED`
* Terminal rewards: `+1` / `0` / `-1` (see [Verifiers](/environments/mechanics/verifiers)

## Health

```bash theme={null}
curl -s https://agi.akhara.ai/health
curl -s https://agi.akhara.ai/dashboard/health
```