Environment provisioning

An environment is the sandboxed world a task runs against: the simulated services, the seed data, and the transport the agent and user use. Environments give you deterministic, replayable runs without touching production systems.

Environment shape

{
  "id": "env_medical_triage",
  "name": "Medical Triage",
  "port": 8931,
  "service": "triage-sim",
  "userTransport": "android-emulator",
  "cats": ["healthcare"],
  "tags": ["phi", "triage"],
  "version": "1.2"
}

Installed env ids are derived from the hub id with dashes → underscores (medical-triage → env_medical_triage).

Provision one

akhara init my-triage-env --template medical-triage
cd my-triage-env
akhara deploy        # boots the sandbox, prints the env_id + port

POST /api/agents/health-ai/provision

The provisioning flow

Provisioning runs a fixed five-step boundary setup, surfaced live in the console diagram (Simulated Services → Agent → User transport):

Step	Key	What happens
1	`image`	Resolve the environment image.
2	`sandbox`	Start the isolated sandbox boundary.
3	`seed`	Seed sample data (patients, catalog, …).
4	`agent`	Wire the agent profile and inject `env.GATEWAY`.
5	`ready`	Environment ready for runs.

Step 4 injects a GATEWAY env var (e.g. https://api.akhara.dev) so the PEP inside the sandbox reaches the PDP, enforcement stays in-path even in an isolated boundary. Created environments persist to akhara.created-environments.v1.

The boundary

The agent’s runtime boundary (for example android-emulator) determines how the user transport and simulated services are wired:

Next: run

Evaluate offline and enforce live.

Get started

How it works

Enterprise onboarding

SDK

Environment provisioning

Environment shape

Provision one

The provisioning flow

The boundary

Next: run

​Environment shape

​Provision one

​The provisioning flow

​The boundary

Next: run

Environment shape

Provision one

The provisioning flow

The boundary