Codex for Knowledge Work
A power-user’s guide to turning OpenAI’s coding agent into an operating system for knowledge work, including setup, workflows, and a seven-day starter plan
Codex is easy to underestimate. At first glance, it looks like another AI coding tool; if you’re not an engineer, a natural conclusion is that it’s not for you.
That reading misses how much Codex makes possible.
Picture a Monday morning: A request for a launch plan lands in your inbox. You open the right Codex project, give it the brief, and close your laptop while Codex works in the cloud. On your commute to the office, you get a notification on your phone: Codex has read the pertinent Slack threads, pulled customer notes out of Google Drive, checked last quarter’s numbers in PostHog, and started a go-to-market plan in a shared Notion document. It just needs you to confirm one detail about timing, which you do with a thumbs-up. By the time you reach your desk, a draft is waiting for review.
This is what agent-native knowledge work looks like. It all runs on OpenAI’s agent, Codex, in the Codex desktop app. We use “Codex” to refer to the app throughout this guide.
Codex is a workspace for you and your AI agents. Give Codex access to the files, apps, and tools it needs, and it gathers the context it needs, uses the tools you’ve connected, and works through the task. The same capabilities that make it useful for code apply to a broad range of knowledge work.
There are two ways to work with agents in Codex: delegate or collaborate.
- Delegate tasks that are predictable, repeatable, and low-risk. With clear, well-specified instructions, the agent can execute autonomously and bring back finished work for your review.
- Collaborate on tasks that are judgment-heavy, exploratory, or iterative. You work alongside the model toward an outcome that matches your vision.
AI can now perform tasks that once required specialized expertise, which creates both more opportunity and more noise. The people who work best with AI know what to delegate and what to decide themselves. They ride the models rather than being overwhelmed by them.
Expert Codex users are clear examples of what that looks like in practice.
This guide is about becoming one of those people. It covers how to set up a workspace, run high-leverage knowledge-work tasks, and turn repeated work into durable systems that get better over time. If you’re ready to think of your work in terms of cycles instead of one-off tasks, this guide is for you.
You do not need every Codex capability at once. Learn what is available, then choose the level of delegation, customization, and automation that matches your comfort, trust, and ability to review the result. A higher level is not automatically better; as Every’s “Eight Levels of AI Adoption” guide argues, sophisticated users move between levels according to the task.
Updated June 2026
Part 1: Understanding Codex
What Codex is
Codex is an agentic workspace: You give it a goal, and it plans the work, uses available tools and context, and produces a result for you to review. It can read and write files in the project folder you open, work with external services through plugins and apps, run multi-step workflows, generate code and scripts when a task needs them, and create documents, spreadsheets, presentations, PDFs, and websites.
Codex can:
- Work alongside you on multiple tasks in parallel
- Pull context from the apps and files you connect
- Use a supported browser and desktop workflows when a task needs on-screen action
- Check its work and iterate toward a defined goal when it has the context, tools, and permissions it needs
- Hold a persistent goal across a long-running session, instead of treating each message as a one-off request
- Turn repeatable tasks into recurring workflows
- Package reusable instructions as skills and installable plugins
- Turn plans, reports, and working material into hosted Sites
- Let you start, steer, and review work from your phone while Codex runs on a connected computer
These capabilities make Codex useful both for delegating well-specified tasks and as a shared workspace for human-agent collaboration. The central judgment call is deciding which mode fits the task.
This guide is for paid subscribers
Upgrade your membership to continue reading the full guide.
Subscribe to continue