t4-p3-06authored2–4h
Retrospective
requires: t4-p3-05
Spec
A short written retro: what you would do differently, what surprised you about real usage against your Phase 1 hypothesis, and what you would build next if you continued.
Why this matters
The hypothesis being wrong is a valid and often better outcome than it being right. The retro is where the track's whole arc - validate, build, measure - either closes honestly or reveals it was never really tested.
Verify
No result yet. Run `learn verify t4-p3-06` locally, or push to trigger CI.
artifact
unrun
judge
unrun
Rubric
# t4-p3-06 — Retrospective
**Task:** A short written retro: what you would do differently, what surprised you about real usage against your Phase 1 hypothesis, and what you would build next if you continued.
**Strong:** Directly answers every one of the review questions below in the affirmative, with specific evidence from the actual work, not a restatement of the task.
- Is the Phase 1 hypothesis explicitly revisited and judged?
- Does real usage contradict any prior assumption? A retro with no surprises is usually incurious.
**Passing but weak:** The deliverable exists and technically satisfies the spec, but is generic, restates the task instructions instead of engaging with them, or only partially addresses the review questions below.
**Fails:** The deliverable is missing, or engages with none of the review questions below - e.g. it describes what was built without explaining the reasoning the task actually asks for.