10 Rules for Building AI Agents That Actually Work

I've spent the last year building AI agents and working with CEOs doing the same. Most of what I built, I threw out. Here are the 10 rules that survived.I've been building agents across my coaching practice, content production, and business operations — and the biggest lesson is that the hard part isn't the AI. It's codifying what actually matters in your work and organizing it so agents can use it. In this episode, I break down 10 rules for building agents that are genuinely useful — from structuring your data and building context that compounds, to choosing the right model for the right job, mixing deterministic software with LLMs, and managing agents the way you'd manage a high-performing team. No hype, no theory — just what I've learned from doing it every day. If you've been curious about agents but haven't started yet, this is your playbook.Chapters00:00 Introduction00:44 Rule 1: Put All Your Data in One Place02:00 Rule 2: Build Context That Compounds03:28 Rule 3: Design for Rapidly Swapping Models05:03 Rule 4: Use the Right Model for the Right Problem06:55 Rule 5: Mix Deterministic Software with LLMs08:21 Rule 6: Orchestrate Based on Frequency and Value10:44 Rule 7: Keep Agents Narrowly Focused12:04 Rule 8: Get Ready to Iterate12:52 Rule 9: Managing Agents Is a New Skill15:00 Rule 10: Half of What You Build Is Disposable17:11 Your Next Steps: Just Start BuildingFollow Keith Cowing on LinkedIn: https://linkedin.com/in/keithcowingJoin the Inner Circle: https://execs.tvSubscribeYouTube: https://www.youtube.com/playlist?list=PLU_rgycqchjl1jNqjOeJFepyr9yfcXWcMSpotify: https://open.spotify.com/show/1Bw7KhjlUzFjMoFhdfNAKNApple Podcasts: https://podcasts.apple.com/us/podcast/executives-unplugged/id1769131263