Show HN: Stage – Putting humans back in control of code review

Re:Show HN: Stage – Putting humans back in control of code r... by gracealwan on Thursday April 16, 2026 @05:12PM (#47799555)

Totally different part of the reviewing experience, but I would love to see PR comments (or any revisions really) be automatically synced back to the context coding agents have about a codebase or engineer. There’s no reason nowadays for an engineer or a team of engineers to make the same code quality mistake twice. We manually maintain our agents.md with codebase conventions, etc, but it’d be great not to have to do that.

[ Parent | on HN ]

Re:Show HN: Stage – Putting humans back in control of code r... by dean_stratakos on Thursday April 16, 2026 @05:19PM (#47799626)

100%. A big part of code review in my mind is to automate away specific mistakes and anti-patterns across a team. I think there are a lot of interesting things to be done to merge the code writing and code reviewing cycles.

[ Parent | on HN ]

Re:Show HN: Stage – Putting humans back in control of code r... by t0mas88 on Friday April 17, 2026 @03:53AM (#47803516)

I've been working on that as a small open source tool: https://github.com/smithy-ai/smithy-ai

It keeps a repository with markdown files as the agent context, makes those available (via a simple search and summarise MCP) and when closing a merge request it checks whether the context needs updating based on the review comments. If it needs updating a PR is opened on the context repository with suggested changes/additions.

[ Parent | on HN ]