AI-Powered Code Review
Workshop
Every engineering organisation is experimenting with AI coding assistants, but few have built production-grade LLM integrations into their core developer infrastructure. I have such an experience, and I will share real patterns from deploying an AI-powered code review system across a 400+ person engineering organisation (~200 developers) — covering a competitive evaluation of 4 tools across 18 dimensions, building a webhook-based review architecture with slash commands and auto-review, evolving context enrichment from static rules to AI-powered document selection, managing a 4-model fallback chain on Vertex AI, and measuring impact through a feedback dashboard. Attendees will leave with a battle-tested
playbook for integrating LLMs into their own engineering workflows — not as toys but as production infrastructure.
Workshop Structure
1. The Code Review Bottleneck at Scale
2. Tool Evaluation — 4 Candidates, 18 Dimensions
3. Architecture — Webhook Server & Auto-Review
4. Context Enrichment — From Path Rules to AI- Document Selection
5. Model Strategy — Migration & Fallback Chain
6. Measuring Impact — Feedback Dashboard
playbook for integrating LLMs into their own engineering workflows — not as toys but as production infrastructure.
Workshop Structure
1. The Code Review Bottleneck at Scale
2. Tool Evaluation — 4 Candidates, 18 Dimensions
3. Architecture — Webhook Server & Auto-Review
4. Context Enrichment — From Path Rules to AI- Document Selection
5. Model Strategy — Migration & Fallback Chain
6. Measuring Impact — Feedback Dashboard