GoKawiilCritic tool lets reviewers query the AI coding agent that wrote the code
A new tool called Critic routes review questions from a code-change page directly to the coding agent's original session rather than a generic assistant. It uses a short lease system so exactly one connected author device answers a question at a time, and if that device disconnects, the task returns to the queue after 45 seconds without losing context. Questions can be queued even if all author devices are offline, and session transcripts remain stored locally on the originating machine.
GoKawiil's interpretation of the reporting above, not reported fact.
Keeping transcripts on the author's device rather than centralizing them suggests a design choice favoring privacy and continuity of context over convenience of a shared cloud record. The lease-and-reclaim mechanism indicates an attempt to make asynchronous, multi-device AI-assisted coding review feel reliable despite devices going offline unpredictably. This approach could influence how future code-review tools integrate AI agents that retain memory of why code was written, not just what it does.
- Critic routes review questions to the specific AI agent session that wrote the code
- A 45-second lease system reassigns questions if the connected device drops offline
- Session transcripts are kept on the author's own machine rather than centralized
Source: critic.run, 2026-09-24
Published there as: “Show HN: Critic – Review code with the agent that wrote it”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.