t2-p3-04authored5–8h

AI-built feature with a structured review

requires: t2-p3-03

Spec

Build one remaining feature - recurring tasks, say - primarily with a coding agent. Then review the output against a checklist you wrote yourself covering scalability, security, error handling and test coverage, and document what you had to fix in docs/ai-review.md.

Why this matters

Writing the checklist before reading the diff is the entire exercise. Reviewing agent output without one reliably degrades into "it runs, ship it", which is how subtle tradeoffs enter a codebase unexamined.

Verify

No result yet. Run `learn verify t2-p3-04` locally, or push to trigger CI.

artifactartifact: docs/ai-review.md

unrun

reporepo: commit_precedes

unrun

judgejudge: docs/ai-review.md

unrun

Rubric

# t2-p3-04 — AI-built feature with a structured review

**Task:** Build one remaining feature - recurring tasks, say - primarily with a coding agent. Then review the output against a checklist you wrote yourself covering scalability, security, error handling and test coverage, and document what you had to fix in docs/ai-review.md.

**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.

- Did the review find anything real, or conclude the output was perfect?
- Are findings specific to this diff rather than generic advice?

**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.