Inconsistent code review quality and adherence to undocumented project knowledge across varying skill levels in development teams

Signals over time

2 observed signals across 1 sources, tracked for 0 days. Confidence: low.

What people are saying Observed

• “Author here. epho was something we were using internally to build an AI data engineer for a long time, and we thought it had use cases beyond that. One I have recently been exploring is code review. We all know our local dev environments arent shaped the same. Different tools, different repos, different memories in your agent. So I thought a team-level reviewer that lives in CI would help. In the post I also added a small experiment on a small repo where I ran around 90 reviews. If you wanna try it out it's at epho.io. Happy to answer questions”

  Hacker News · question

• “I built a review skill that has a bit of custom project knowledge, our team's agreed engineering standards & tools, a standardised format of how it should respond, and instructions to check for PR description accuracy as well as meeting all ticket requirements. This kind of offloads the responsibility of deep code review to the planning phase: ensure the ticket spec is correct for what needs to be done on a product/team/technical level, and verifying daily CRUD app code is a breeze. Human judgement of the review is still required, because the biggest way issues slip through is through one-slice "it looks fine in this issue" solutions that actually violate undocumented project knowledge. To remedy that , we've started storing architectural decision records in the repo as well. Basically, the more context you can give it (duh), the better agents are at review of day to day work. Taking this approach helps in teams of varying skill levels to standardise the kind of expected feedback on PRs, as well as letting developers run a self-review whether they wrote some code with AI or not. There's still plenty of review feedback going back and forth on P”

  Hacker News · frustration