Skip to main content
Runtime lets AI agents propose infrastructure changes while keeping humans in the loop. Agents can request features, secrets, and permissions - humans review and approve.

How it works

  1. AI agent creates runtm.requests.yaml with proposed changes
  2. Human reviews the proposed changes
  3. Human runs runtm approve to merge changes into runtm.yaml
  4. Human deploys

The requests file

AI agents propose changes by creating runtm.requests.yaml:

Reviewing changes

Preview what would change:

Applying changes

If everything looks good:
This merges the requested changes into 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:
Always include a reason field explaining why each change is needed. It helps humans make informed decisions.
In v1, runtm approve is informational only - deployments work without approval. Future versions will enforce policy compliance for organizations.