@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
@0xQiYan: Installed Codex and not using it to make money? Are you waiting for it to collect dust? Many people, after installing Codex, only use it to modify code or write scripts. But I think a more imaginative use is to have it participate in the entire video production process. By equipping Codex with these 6 GitHub video Skills, it becomes not just a code-writing tool...
Introduces how to install 6 GitHub video skills for Codex, used for the complete video production process including scripts, storyboards, editing, rendering, etc., and recommends combination plans.
@Gorden_Sun: https://x.com/Gorden_Sun/status/2071484947391823966
A detailed guide on how to apply Codex to office and knowledge scenarios, covering environment setup, core concepts, five advanced levels, and other practical content.
@FakeMaidenMaker: This is probably the most complete Codex practical course yet — author Riley Brown spends 30 minutes walking through 7 real white-collar work scenarios, showing you one by one how to boost efficiency with Codex: - Auto OCR 60 receipt photos into Excel - Scan two weeks of emails and organize…
This content introduces the seven major capabilities of the AI agent Codex, demonstrating how to improve work efficiency through 7 real white-collar work scenarios (such as OCR receipts, organizing emails, creating PPTs, etc.), making it a complete practical tutorial.
@Luckyjudy666: 8 Tips to Make Codex Your Personal Assistant 1. Build a Shared Memory for Codex Core rules go in Agents.md, project background in Obsidian, repeated processes as skills, personal preferences and common questions in Memories. Otherwise, Codex is like a new colleague every time, having to explain everything from scratch...
This article shares 8 tips for using the Codex AI assistant effectively, including building shared memory, remote task execution, scheduled automation, file organization, and teaching new software operations, all aimed at improving work efficiency.
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.