Every engineering organisation is experimenting with AI coding assistants, but few have built production-grade LLM integrations into core developer infrastructure. This talk shares real patterns from deploying an AI-powered code review system across a 400+ engineer organisation — covering tool evaluation, webhook architecture, prompt engineering for company-specific rules, model migration, and cost management. Attendees leave with a battle-tested playbook for integrating LLMs into their own engineering workflows as production infrastructure.

Serhii Yakovenko is a software engineer and AI infrastructure specialist. He has experience building scalable developer platforms, integrating LLMs for production code review, flaky test detection, and creating real-time observability dashboards with Redis at large engineering organizations.