• multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.
• grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.

Generating AI review comments is easy; the hard parts are factual grounding in the diff, codebase-specific conventions, and latency. This lays out the architecture and accuracy engineering behind a 63.9% acceptance rate at ~79,000 reviews a week.

• articleEngineering Linkedins Hiring Assistant For International Markets
• articleSemantic Search For Ai Agents At Scale Retrieval And Ranking For Linkedins Hiring Assistant
• articleQa Agent Reimagining Software Quality With Ai Driven Autonomous Testing
• articleThe Training Infrastructure Behind Ai Powered Job Search Eight X Faster Multi Teacher Distillation

• postAI coding agents can generate features fast, but can package them in one giant, github
• articleLearn how to turn one giant AI-generated pull request into a clean, reviewable sgithub
• articleBuilding a software factory for AI SDKLars Grammel

Checking sign-in…

Loading comments…