Automations
Repeatable agent runs started by time or events, with explicit inputs, permissions, outputs, review gates, and recovery behavior.
Use it when
- The same source collection, triage, report, or maintenance task repeats on a schedule.
- Inputs and completion checks can be stated before the run begins.
- Failures can alert an owner and be retried without duplicating side effects.
Choose another layer when
- Irreversible, high-impact decisions without human approval.
- A process whose output cannot be evaluated or traced to its inputs.
Production path
Build it in this order
- 01
Stabilize the manual workflow
Run the task interactively until inputs, decisions, output format, and common failures are known.
Quality check: Different operators can produce equivalent reviewed results.
- 02
Bound permissions and side effects
Use least-privilege credentials, idempotency, approval gates, timeouts, and isolated environments.
Quality check: A retry cannot duplicate a message, payment, deployment, or destructive change.
- 03
Operate it like production
Record source revisions, run logs, artifacts, costs, and quality checks; alert a named owner on failure or drift.
Quality check: Every run is discoverable, explainable, and recoverable.
Artifacts you may see
- .github/workflows/*.yml
- cron configuration
- workflow manifests
- run logs and artifacts
Connected layers
Evidence ledger
Primary documentation behind this guide
Provider-specific behavior is sourced to that provider. Open standards are sourced to their specifications and official maintainers.