Workshop 2 - When code is cheap, governance is the hard part
Code generation is close to free now. Review, sign-off and audit are not, and that gap lands on engineering leaders. Bring a laptop, this one is hands on from minute five. You will take a repository, ask an AI agent to change it, then close the loop. Put your standards where the agent reads them. Wire a live rules check into the agent's own turn over MCP. Make it fix its own violations before the code reaches you. You leave with a working repository, the configuration and a reusable skill, running on whatever AI coding tool you already use. I'll draw on what we've learned governing 950+ enterprise SaaS instances, with scan data going back to 2017: where AI-generated changes fail before production, and how automated checks and audit trails hold humans and AI to the same standard without slowing releases. Level: practitioner. Prerequisites: a laptop, git, Node 20 or later, a GitHub account, and an AI coding tool you can sign into (Claude Code, Cursor, Codex, Windsurf, Replit or any MCP client).
