Episode Details

AI coding tools like Claude Code, Codex, Cursor, Lovable, Replit, and Bolt are making it possible for non-engineers to build real internal software. But when does an AI-built app become risky enough that you need a professional software team to review it? In this episode, Justin Davis and Greg Ross-Munro break down the difference between low-risk internal tools, high-risk production systems, and the tricky middle ground where business value, customer data, integrations, and security all matter. They also explain why “vibe coding” is evolving into “agentic engineering,” and how service firms can use these tools safely without creating avoidable technical, operational, or legal risk.