← back
Full Workshop: Setting Yourself Up for Success —Jason Liu, OpenAI Codex
Takeaway
Invest in persistent context and shared workflows so agents support ongoing projects across coding and knowledge work.
Summary
- Liu demonstrates using the Codex app for coding, evaluations, presentations, video editing, documentation, and operational work.
- He reports maintaining long-lived project threads through compaction and advocates pinned threads, personal memory, and recurring automations.
- Dictation and computer-use context capture reduce the effort of communicating intent and showing the agent relevant material.
- Reusable team skills and plugins encode review standards; communicating project threads are presented as a path toward coordinated delegated work.
codexpersistent-memoryworkflow-automation
Original description
Jason Liu walks through how Codex works as a general tool for controlling your computer: setting up a memory vault and assistant threads, prompting it to collaborate with other threads, exploring computer use, thinking about long-running work streams, and preparing to work in loops. Speaker: Jason Liu — Developer Experience, OpenAI Jason helps developers get more from Codex, the Agents SDK, and the OpenAI API. Before OpenAI, he created Instructor and taught developers how to build reliable AI applications. X/Twitter: https://x.com/jxnlco LinkedIn: / jxnlco Website: https://jxnl.co/