Exploring Next

Exploring Next — Ep 305 w/ Justy & Cody — Harness engineering for coding agent users

Justy and Cody dig into harness engineering for coding agents: the practical idea that trust in AI-written code comes less from the model itself and more from the guardrails, checks, and feedback loops wrapped around it. They unpack feedforward guides versus feedback sensors, deterministic tooling versus LLM-based judgment, and why teams should treat the human as the person tuning the harness instead of reviewing every tiny diff forever.

Open source article

Full episode page with transcript →

Browse all Exploring Next episodes →