Mission #01 · Intermediate
Observe prompt & model assets
Use the public ingestion boundary to register observed asset identity while keeping prompt authoring and model serving in your own runtime.
STEP 01
Start AI Governance Platform locally
Start the local stack from your AI Governance Platform checkout.
Run in your AI Governance Platform checkout./servers.shExpected outcome
The launcher finishes and Studio is available locally.
STEP 02
Open Local Studio
Sign in to Studio with the local development credentials from your Keycloak environment.
Expected outcome
You reach the Studio home screen and can open the Assets workspace.
STEP 03
Prepare your producer credentials
Set the local API URL and use a bearer token obtained through your configured identity provider.
Run in your AI Governance Platform checkoutexport AI_GOVERNANCE_API_URL=http://localhost:8000 export AI_GOVERNANCE_TOKEN=replace-with-a-bearer-tokenExpected outcome
Your producer has the values it needs to call the public observation API.
STEP 04
Report an observed prompt
Submit the immutable prompt identity used by your runtime.
Run in your AI Governance Platform checkoutcurl -X POST "$AI_GOVERNANCE_API_URL/api/v1/prompts/observations" \ -H "Authorization: Bearer $AI_GOVERNANCE_TOKEN" \ -H 'Content-Type: application/json' \ -d '{ "name": "support-assistant", "version": "v7", "source_system": "support-api", "source_reference": "evaluation-run-123", "content_hash": "sha256:replace-with-the-runtime-hash", "variables": ["question", "context"] }'Expected outcome
The API accepts the observation. Repeating the identical request is idempotent.
STEP 05
Verify the observed evidence
Find the new record in the Prompt Catalog and inspect its source metadata and lineage.
Expected outcome
The asset is labelled Observed; content remains unavailable when you supplied only a hash.
