I had a handful of parallel Claude agents write me up a strategy folder for a side project. The pull request looked great: ten documents, all neatly cross-linked, and it read well. Then the automated reviewer posted its findings, and Claude, to its credit, did not object: Claude conceding, mid-session: “The automated review caught a…
OpenAI’s Codex now hides what its AI agents tell each other. Developers can no longer see how tasks get delegated internally. Since early June, OpenAI’s coding tool Codex has encrypted the instructions a main agent passes to its subagents. Coding tools are increasingly turning into agentic systems that break down tasks, delegate parts to subagents, and make…
It covers both the regular ChatGPT interface and Codex in a single framework, reflecting how the two are converging into one product. The tone is a bit different from OpenAI’s recent developer docs for GPT-5 and GPT-5.5, which focused on API parameters, reasoning-effort levels, and elaborate prompt schemas. The end-user guide drops all of that but keeps…