OpenAI engineer Jason Liu shares Codex workflow post
Jason Liu, Developer Experience Engineer at OpenAI on the Codex team, shared a draft post on his personal site outlining daily workflows for the tool. The post describes extending Codex beyond code changes into knowledge work such as Slidev presentations and voice note-taking beginning around November. Liu specifies five requirements for sustained tasks: durable threads, memory stores, computer-wide tools, recurring schedules, and review surfaces. He explains compaction via pinned megathreads and Command-1 to Command-9 shortcuts while noting higher inference costs for older threads. Other users recommended the post as useful reading.
@jxnlco Hi Jason
jason from the codex team here, heres a draft on codex maxxing and the primatives i use on a daily basis https://jxnl.github.io/blog/writing/2026/05/10/codex-maxxing/ would love any feedback
jason from the codex team here, heres a draft on codex maxxing and the primatives i use on a daily basis
would love any feedback