I Let AI Handle More of Its Own Review Feedback. Then I Had to Give the Work Boundaries
说明与用途
在 AIDD Skeleton 仓库中使用 AI 代理自动化处理审查反馈,能够更广泛地调查问题,但限制修改范围,挑战自身修复,并保留推迟的工作以供后续考虑。
问题
External reviewers find issues, but letting an AI implementation agent handle them autonomously risks endless task expansion and silent scope creep.
结果
The author achieved a balanced AI‑review workflow that allows autonomous investigation while preventing scope creep, ensures corrections are self‑challenged, and preserves deferred work for future action.
工作流
- 1. Reviewer reports a finding.
- 2. AI investigates beyond the exact location, asking what assumption failed and where else it matters.
- 3. AI determines if the finding is valid and assigns a disposition: Accept now, Reject, Defer, or Observe.
- 4. If accepted, AI applies the fix but treats the correction as a new adversarial surface, challenging it in subsequent reviews.
- 5. If the same issue recurs, AI triggers Structural Reassessment to examine underlying design or invariants.
- 6. Deferred items are stored in workbench/ with reason, context, and reconsideration conditions.
- 7. The process repeats until all findings are resolved or deferred items are revisited.
证据
The implementation agent already had the repository context. Ideally, one useful finding should let it investigate further on its own.
The better the agent became at finding related issues, the easier it became for the current task to expand indefinitely.
I stopped treating review findings as isolated lines.
- 记录日期: 2026-09-16T03:00:44.955Z