@FinanceYF5: How to Maximize the Value of Codex 1/ Jason Liu Redefines Knowledge Work with Codex Codex team DX engineer, Instructor founder jason says: Codex is not just about writing code. It has become a hub that crosses tool boundaries to handle slides, PDFs, ...
Summary
Jason Liu shared how to use Codex as a central hub to handle knowledge work across tools, such as slides, PDFs, spreadsheets, to maximize its value.
View Cached Full Text
Cached at: 05/18/26, 10:30 AM
🧵How to Maximize the Value of Codex
1/🧭 Jason Liu Redefines Knowledge Work with Codex
A Codex team DX engineer and founder of Instructor, Jason says: Codex is not just about writing code
It has become the core hub for handling slides, PDFs, and spreadsheets across tool boundaries. 👇 https://t.co/UwrB8wkCAC
2/ He pins a thread for each core workflow
Staff threads, Agent SDK, open-source Codex… these are not chat logs,
but “persistent threads” that accumulate months of preferences, decisions, and context — the agent never needs to start over when it returns.
3/ The value of voice input isn’t speed, it’s rawness
The agent gets Jason’s unedited raw thoughts, not a polished version.
“I remember Ben mentioned this on Slack, go check it out” — typing is too cumbersome, but saying it out loud is incredibly natural.
4/ The “pivot” feature lets him direct while watching, no waiting
While previewing a website, he says aloud: shrink it, there’s a typo, spacing is off, submit a PR, wait for deployment, send to Slack for review…
The agent executes while he’s already moved on; a queue has formed.
5/ He built his memory system on top of an Obsidian Vault
The repository stores code, the Vault stores dynamic context: people, decisions, project status.
The agent updates the Vault, Jason reviews the diff — this audit step is critical to prevent memory bias from silently accumulating across conversations.
6/ Heartbeat mechanism: letting loops run automatically across tool boundaries
His staff thread checks Slack and Gmail every 30 minutes, with draft replies already waiting in his drafts.
Animation project case: heartbeat monitors Slack feedback → re-render → auto-reply tagging reviewers. He’s not there, but the loop keeps running.
7/ The only change he truly cares about comes down to one sentence:
Work shouldn’t pause when you step away.
Threads keep running, memory keeps updating, feedback keeps being processed — even while you take a shower, the refund is already done.
This is what an AI agent should look like.
Full content:
That’s all, original author @jxnlco
If you like this topic:
- Follow me (@FinanceYF5)
- Like + retweet the first post below
Similar Articles
Codex is becoming a productivity tool for everyone
OpenAI's new report shows Codex expanding beyond coding to become a productivity tool for knowledge workers, with over 5M weekly active users and rapid growth in non-developer tasks like data analysis and workflow automation.
Codex-maxxing
Jason Liu shares how he uses OpenAI's Codex for knowledge work beyond coding, leveraging durable threads, voice input, and steering to integrate coding agents into his broader workflow.
@FinanceYF5: Wow, the whiteboard feature in Codex is absolutely mind-blowing. It can directly grab thumbnails from YouTube or any website and put them on the whiteboard, allowing you to quickly organize various concepts. Each image is an independent element, and you can freely mix and match them using Codex's built-in GPT-Image 2 model.
Codex's whiteboard feature can grab thumbnails from YouTube or any website and freely combine them using the built-in GPT-Image 2 model, making it easy to quickly organize concepts.
@jxnlco: jason from the codex team here, heres a draft on codex maxxing and the primatives i use on a daily basis https://jxnl.g…
Jason Liu shares his workflow primitives for using Codex effectively, including durable threads, voice input, and steering to extend AI agents beyond coding into knowledge work.
How finance teams use Codex
OpenAI highlights how finance teams can leverage Codex to automate tasks like generating monthly business review narratives and cleaning up financial models, integrating with tools like Excel and Slack to improve efficiency.