Human approval gates
Goal: design an AI workflow where risky action pauses for review instead of letting automation run loose.
Outcome
You should finish with an approval-state diagram, an audit log plan, and a list of actions that require human review.
Example AWS shape
- Workflow orchestration: AWS Step Functions for explicit states.
- Task execution: Lambda functions with scoped IAM permissions.
- Events: EventBridge for routing review-needed events.
- Logging: CloudWatch Logs for state transitions and decision records.
- Storage: DynamoDB or S3 for approved test artifacts.
Approval gates to model
- Outbound messages.
- Public publishing.
- Payment or checkout changes.
- DNS, backend, or production changes.
- Access to sensitive data.
- Deleting, overwriting, or moving files.
Runbook steps
- Draw the workflow as draft, review, approved, executed, and logged.
- Write one example payload that should stop for review.
- Write one example payload that can proceed automatically.
- Design the log fields: request ID, actor, action, risk level, approval state, timestamp, and result.
- Explain how rollback would work if the approved action creates a problem.
Portfolio artifact
Create an approval-gate README and a workflow diagram. The point is to prove that you understand AI security is not only model safety. It is operational control.