How it works
- AI agent creates
runtm.requests.yamlwith proposed changes - Human reviews the proposed changes
- Human runs
runtm approveto merge changes intoruntm.yaml - Human deploys
The requests file
AI agents propose changes by creatingruntm.requests.yaml:
Reviewing changes
Preview what would change:Applying changes
If everything looks good:runtm.yaml and deletes the requests file.
To reject, simply delete the file:
What agents can request
Features
Environment variables
Egress allowlist
For agent developers
If you’re building an AI agent that integrates with Runtime:In v1,
runtm approve is informational only - deployments work without approval. Future versions will enforce policy compliance for organizations.