AI Writes More PRs. Who Validates Them? — Ali-Reza Adl-Tabatabai, Sonar

Why watch

This talk addresses the challenge of AI-generated code overwhelming CI and code review processes, presenting agentic validation as a solution. It targets platform engineers, DevOps teams, and technical leads who need to handle increased PR volume from AI coding assistants while maintaining code quality. The presenter demonstrates how automated PR review, CI failure analysis, autofixing, and auto-merging can scale with AI-generated code using SonarQube's program analysis combined with LLM agents.