307 - Harness Engineering - the hard part of AI coding

The hard part of AI coding isn't generating code — it's controlling quality, safety, and drift. Kaushik and Iury break down harness engineering: the five pillars for shaping an agent's environment and what it looks like when teams build custom harnesses from scratch. Full shownotes at fragmentedpodcast.com. Show Notes Why it matters Harness Engineering - Shaping the harness The Feed's Lost and Found - Agent legibility Closed feedback loops Persistent memory Entropy control Blast radius controls Building the harness Minions: Stripe's one-shot, end-to-end coding agents - Goose - open-source coding agent from Block Superpowers by Jesse Vincent - skills Open Code - open-source coding agent you can fork and Other resources Agent Harness Glossary - Towards self-driving codebases - Agentic Workflows - Future of Software Development - Get in touch We'd love to hear from you. Email is the contact page for other We want to hear all the feedback: what's working, what's not, topics you'd like Contact us Newsletter Youtube Website Co-hosts: Kaushik Gopal Iury Souza [!fyi] We transitioned from Android development to AI starting with Ep. #300. Listen to that episode for the full story behind our new direction.