Workflow automation in code
Mastery: ship checklist
A second person can reproduce fixture thread reaches awaiting_approval with draft; send blocked until Approve(id) from a clean checkout and name the owner for WF-AUTOSEND-19.
1Learn the idea
Read
Clean-room demo
From a fresh clone/directory, run the commands that prove fixture thread reaches awaiting_approval with draft; send blocked until Approve(id). A second person plays ops coordinator clearing a 200-message backlog without auto-sending refunds and follows your script without coaching. The demo includes limitations: what typed workflow that classifies inbound email → draft reply → human approve → send still will not do.
Read
Evidence pack
Bundle: contract snippet, passing tests, metric snapshot for unapproved_send_count == 0 and median_time_to_draft ≤ 45s, security negative probe, rollback note, owner name. Reference WF-AUTOSEND-19 as the drill you rehearsed. If any item is missing, the ship gate fails even if the happy path dazzles.
Read
Implementation artifact
test("no autosend", async () => {
const spy = vi.fn();
await runFixture("refund-plea.txt", { send: spy });
expect(spy).not.toHaveBeenCalled();
});
Read
Ownership and next review
For Workflow automation in code, name the human who gets paged, the review date for thresholds, and the condition that triggers reevaluation. Endpoint POST /v1/workflows/email-triage/runs remains the production surface you operate for typed workflow that classifies inbound email → draft reply → human approve → send — not a slide. Keep WF-AUTOSEND-19 in the handoff template so the next owner inherits the drill.
Read
Stage depth
After the peer demo, schedule the next threshold review date. File a short changelog that mentions WF-AUTOSEND-19 and the control that addresses it. Archive the evidence pack where your team already stores launch records. Resist rewriting everything “for real production” in one weekend — operate this slice until the metrics bore you, then widen. Final self-check: if telemetry vanished, would you still know to hold? If yes, you learned the operating posture this lane teaches.
Read
Field notes for `workflow-automation-code` / `mastery-ship`
Trim the demo script until every command is necessary. Record a peer signature line: name, date UTC, pass/fail. File known limitations as bullets, not apologies. Link the evidence pack from the README. Schedule the next game day on a calendar, even if it is solo. Archive the branch tag or release digest you actually shipped. 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
Draft a two-minute demo script that proves fixture thread reaches awaiting_approval with draft; send blocked until Approve(id) from a clean directory. Include the failure rehearsal for model labels 'issue refund' and workflow auto-calls payment tool and the rollback/owner line. If the script needs tribal knowledge, the lab is not shipped.
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.