Winners of GitLab AI Hackathon

Works inside code review: spots the security bug, writes the fix, and opens the merge request — no human needed.

Maps code dependencies and shows how systems evolve — see a change's full impact before you make it.

An eight-agent knowledge engine that stops institutional knowledge from walking out the door — router, knowledge graph and dashboard, with 43 tests. A judge called it 'a product, not a hackathon project'.

Explains every decision it makes with AI, deployed to Google Cloud and production-ready.

Three agents — Detector, Writer, Reviewer — fix documentation; confident fixes become merge requests, uncertain ones become issues for humans.

Scans CI/CD pipelines for environmental impact and produces carbon footprint reports.

Verifies AI-generated security reports, closing the trust gap between AI findings and developer action.

Five agents that run database migrations against a safe copy of production — real PostgreSQL, real data, real Google Cloud deployment.