Workflow automation in code
Cover security and operational gates
Least privilege, negative probes, and a timed rollback beat a security essay about typed workflow that classifies inbound email → draft reply → human approve → send.
1Learn the idea
Read
Least privilege for this lab
Separate runtime and operator roles for typed workflow that classifies inbound email → draft reply → human approve → send. Runtime may only perform the narrow actions that ops coordinator clearing a 200-message backlog without auto-sending refunds needs; operators get audited break-glass with TTL. Encode a negative probe that denies the privilege trick related to model labels 'issue refund' and workflow auto-calls payment tool.
Read
Data and secret hygiene
Redact prompts/PII at collection. Secrets enter via a manager or workload identity — never source, fixtures, or exception strings. Incident WF-AUTOSEND-19 should be impossible if these controls hold. Output allowlists and schema checks stay in force on error paths.
Read
Implementation artifact
allowlist.send = ["email.send"]; // payment.refund excluded from this workflow
Read
Rollback drill
Rehearse the rollback or kill switch timed against a clock. Record actor, reason, prior revision/secret/flag, and verification query. Invariant reminder: send step requires approval token; classifier never triggers send directly.
Read
Stage depth
Abuse cases unique to this lab include the privilege path implied by model labels 'issue refund' and workflow auto-calls payment tool. Prove a read-only role cannot mutate. Break-glass tokens expire; leftover tokens fail the drill. Dependency pin/digest story matters when images or models move under you. Document how to rotate the credential that typed workflow that classifies inbound email → draft reply → human approve → send uses without a full outage window longer than your dual-run plan. Security evidence is part of ship, not an appendix nobody reads.
Read
Field notes for `workflow-automation-code` / `security-ops`
List network egress destinations and justify each. Ensure debug endpoints are off by default in the shipping config. Verify that error responses do not echo secrets or raw stack frames to clients. For multi-tenant paths, add a cross-tenant probe fixture. Time the rollback drill twice — once with the author, once with a peer. Store the drill transcript beside the threat notes for the incident id. In this chapter the product is typed workflow that classifies inbound email → draft reply → human approve → send, the human stakeholder is ops coordinator clearing a 200-message backlog without auto-sending refunds, and the incident id you design against is WF-AUTOSEND-19. Re-state the oracle in your notes — fixture thread reaches awaiting_approval with draft; send blocked until Approve(id) — and keep the invariant visible: send step requires approval token; classifier never triggers send directly. Track unapproved_send_count == 0 and median_time_to_draft ≤ 45s as the scoreboard. Surface under change control: POST /v1/workflows/email-triage/runs. If you only have forty minutes, finish the fixture for model labels 'issue refund' and workflow auto-calls payment tool before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.
Go deeper
Before you start
Why this matters
Threat-model typed workflow that classifies inbound email → draft reply → human approve → send in five minutes: who can change config, who can read secrets, what a malicious payload tries to do. Write one negative probe that must yield deny with zero side effects. Reference WF-AUTOSEND-19 as the story you refuse to repeat.
In the wild
See how this idea shows up as a product and a company — then come back to the lesson. Skills transfer across vendors.
Related lessons
Check your understanding
Page assessment
Answer from memory. Completion is saved from this evidence, not from opening the next page.
All responses are required.