Multimodal API lab
Ship and explain the reversible vision endpoint
A second person can reproduce sharp receipt → total=24.50 merchant=Cafe Nora confidence≥0.7; blurry → abstain from a clean checkout and name the owner for VISION-MEME-77.
1Learn the idea
Read
Clean-room demo
From a fresh clone/directory, run the commands that prove sharp receipt → total=24.50 merchant=Cafe Nora confidence≥0.7; blurry → abstain. A second person plays expense bot that must refuse blurry or non-receipt images and follows your script without coaching. The demo includes limitations: what typed receipt-vision API that extracts total + merchant with uncertainty still will not do.
Read
Evidence pack
Bundle: contract snippet, passing tests, metric snapshot for extraction_precision and abstain_on_non_receipt ≥ 0.95, security negative probe, rollback note, owner name. Reference VISION-MEME-77 as the drill you rehearsed. If any item is missing, the ship gate fails even if the happy path dazzles.
Read
Implementation artifact
test("meme abstains", async () => {
const out = await extractReceipt(fixture("meme.png"));
expect(out.abstain).toBe(true);
});
Read
Ownership and next review
For Multimodal API lab, name the human who gets paged, the review date for thresholds, and the condition that triggers reevaluation. Endpoint POST /v1/receipts/extract remains the production surface you operate for typed receipt-vision API that extracts total + merchant with uncertainty — not a slide. Keep VISION-MEME-77 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 VISION-MEME-77 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 `multimodal-api-lab` / `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 receipt-vision API that extracts total + merchant with uncertainty, the human stakeholder is expense bot that must refuse blurry or non-receipt images, and the incident id you design against is VISION-MEME-77. Re-state the oracle in your notes — sharp receipt → total=24.50 merchant=Cafe Nora confidence≥0.7; blurry → abstain — and keep the invariant visible: image ≤ 4 MiB, MIME allowlisted, model output schema-validated before DB write. Track extraction_precision and abstain_on_non_receipt ≥ 0.95 as the scoreboard. Surface under change control: POST /v1/receipts/extract. If you only have forty minutes, finish the fixture for screenshot of a meme parsed as a $9,999 expense 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 sharp receipt → total=24.50 merchant=Cafe Nora confidence≥0.7; blurry → abstain from a clean directory. Include the failure rehearsal for screenshot of a meme parsed as a $9,999 expense 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.