Hours-long AI work depends on workflow, not a magic prompt
The useful pattern is not one perfect prompt, but a setup that lets AI keep working through a clear list of tasks. A normal ChatGPT chat usually cannot work alone for many hours, while Codex goal mode or Claude Code can handle larger coding goals step by step. Codex can keep going with /goal-style instructions, but long runs can burn many tokens and hit cost or .
Long tasks work better when there is a task list, separate task files, clear stopping rules, review steps, and sometimes worktrees for parallel work. Some setups use , a webhook, and scheduled wake-ups so AI checks CI results later and fixes failures. The real use cases are usually , tests, , data checks, or waiting for slow build systems.
Running AI for many hours is not automatically valuable; without a clear problem and clear stop point, it can waste time and money.
Key points
- Long AI work comes from Codex goal mode, Claude Code, or similar setups, not from one special prompt.
- /goal-style runs can continue for a long time but may use many tokens.
- A task list, task files, stopping rules, and review steps make long runs more reliable.
- , a webhook, and scheduled checks can let AI return later and react to CI results.
- The best target is a concrete coding problem, not keeping AI busy for its own sake.