← Back to workCase study 03 / 04
Engati · AI tooling · company award
AI code reviewer
A reviewer that reads the diff first. Code review went from about 2 hours to 30 minutes per developer, and the team made it their default.
2 h → 30 minreview effort per developer
~20developers use it
Defaultthe team’s review workflow
Awardcompany award for the project
(01) The problem
Reviewing a merge request took each developer around two hours. The idea: let an assistant do the first pass on the diff, while a person still makes the final call.
(02) How it works
- A developer asks for a review from Slack.
- The Spring Boot agent pulls the merge request’s diff from GitLab.
- Token-budget preprocessing shapes the diff to fit the model’s context window.
- An LLM writes review feedback.
- The feedback goes to a human reviewer, who makes the final call.
(03) Key decisions
Start in Slack
Reviews begin where the team already talks, so there was nothing new to learn.
Mind the token budget
Large diffs are shaped before they reach the model, so big merge requests still fit in its context.
An aid, not an autopilot
The AI suggests; a person decides. Its output is always checked by a human.
(04) Results
- Review effort per developer: ~2 hours → ~30 minutes.
- Adopted by ~20 developers and became the team’s default review workflow.
- Won a company award.