Found at “Harness engineering: leveraging Codex in an agent-first world” on 2026-03-05T13:44:15+01:00.

Humans always remain in the loop, but work at a different layer of abstraction than we used to. We prioritize work, translate user feedback into acceptance criteria, and validate outcomes. When the agent struggles, we treat it as a signal: identify what is missing—tools, guardrails, documentation—and feed it back into the repository, always by having Codex itself write the fix.