Your teammate says “I used ChatGPT.” That sentence used to mean one thing: a chat box that rewrote an email. In mid-2026 it can mean three different jobs. Someone drafted a status update in Chat. Someone else ran a multi-step office task in Work and handed back a deck outline with a sheet attached. A third person opened Codex, touched a repo, and asked you to review a pull request description. Same login. Same brand. Three different doors.
This is Part 1 of ChatGPT product map. If you finished Learn ChatGPT from scratch, you already know company vs product vs model, plans in broad strokes, and the desktop mode switcher in overview form. Here we slow down and make Chat, Work, and Codex discussable in a meeting. Later map parts cover Custom GPTs, model names without hype, and the API path for builders. Deep Work and Codex tutorials live in their own series after this map is clear.
What you’ll learn
- Plain definitions for Chat, Work, and Codex as job types, not marketing slogans
- Where each mode shows up on desktop, web, and mobile as of writing (July 2026-era map)
- Why agent-style modes burn usage faster than a short conversation
- A one-breath chooser you can use before you start a long task
- Common mix-ups that waste limits, confuse reviewers, or dump the wrong artifact into Slack
Product labels, plan bundling, and which surface gets which feature move. Treat what follows as a dated map. Re-check openai.com/chatgpt, chatgpt.com, and help.openai.com before you write policy or buy seats for a whole team.
Why three modes exist
OpenAI still sells “ChatGPT” as one product family. Under that name, the work you do is not one shape. Some jobs are conversation: you write, you get a reply, you edit, you leave. Some jobs are multi-step office work: you want steps across files, apps, slides, sheets, and docs, with progress you can interrupt. Some jobs are software: repositories, diffs, tests, pull requests. Forcing all three into a single chat thread makes people either underuse the tools or overtrust a chat reply as if it already changed a codebase.
The desktop app is where OpenAI made the split hardest to ignore. As of writing, Chat, Work, and Codex live together in the ChatGPT desktop experience on Mac and Windows. Older standalone Codex builds and “Classic” desktop paths may still show up as migration stories. Web and mobile keep expanding Work and related agent habits by plan, with uneven parity. The durable idea is not the exact menu label. It is the job type.
At work, vocabulary costs money. Finance may approve a Plus seat and still be shocked when agent sessions burn capacity. IT may allow browser Chat and still restrict local folder or coding access. An analyst who only knows Chat will paste CSVs into a thread while an engineer expects multi-file edits in Codex. Name the mode. Plans, permissions, and review habits become discussable once the door has a name.
Chat: conversation, writing, plans, and Q&A
Chat is the default door most people still mean when they say ChatGPT. You lead turn by turn. You type a prompt, maybe attach a file you are allowed to share, read the reply, push back, rewrite, and export. The unit of work is a conversation. That sounds simple. It is also the right tool for a huge share of real jobs.
What Chat is good at
Use Chat when the main artifact is language or judgment inside a thread. Draft an email from bullet notes. Critique a slide outline. Explain a metric definition for non-analysts. Turn messy meeting notes into three options with risks. Translate jargon for a specific audience. Plan a week of tasks without opening five tools. Ask clarifying questions before you touch a spreadsheet. Review one PDF and list open questions. Learn a concept until you can restate it in your own words.
Chat is also where new users should live first. You can learn prompting, verification, and “paste less private data” habits without giving an agent write access to a repo or a folder of contracts. That sequencing matters more than any feature comparison chart. If Chat still feels fuzzy, stay in Learn ChatGPT from scratch before you treat Work or Codex as your daily driver.
What Chat is awkward for
Chat is awkward when the unit of work is a tree of files that must stay consistent, or a multi-step office job that wants intermediate artifacts on disk. You can paste snippets. You are still the glue. You copy, you apply, you re-paste errors, you hope you did not miss a second file that imports the first. Chat is also a weak place to pretend you “ran a project” when all you did was get a long reply that nobody checked against source files.
Chat is still not a source of record. If the answer becomes a board number, a customer commitment, or a SQL change that hits production, a human owns the check. That rule does not change because the UI feels friendlier than last year.
Web, desktop, mobile for Chat
Web Chat is the lowest-friction start: any machine with a browser, IT can often allow-list the domain, and you are not installing software. Desktop Chat is useful when you want a dedicated window, less tab chaos, and the same install that also holds Work and Codex. Mobile Chat is for capture and light review: dictate a thought on the train, reread a draft, kick something that continues later. Exact feature parity still moves, so treat mobile as “great for many tasks, not always identical to desktop.”
Rule of thumb: If the job is thinking, drafting, planning, or Q&A, open Chat first. If the job is multi-step office work with tools and deliverables, look at Work. If the job is changing software in a project, look at Codex.
Work: agentic multi-step office work
Work is the agent-shaped mode for non-coding knowledge work. Think multi-step: gather context, use apps and files you allow, draft longer artifacts, produce something closer to a finished package that you still review. Slides, sheets, docs, and similar office outputs sit in this lane when the product supports them. Work is not “Chat with a longer reply.” It is a different loop: goal, steps, tools, checkpoints, review.
What Work is good at
Work earns its keep when one careful conversation is not enough and the job is still office work, not a software project. Examples that belong here when your plan and permissions allow:
- Turn a folder of meeting notes into a structured brief with open questions
- Build a multi-section report from several sources you explicitly provide
- Produce a first-pass deck outline plus a supporting sheet of numbers you will verify
- Run a longer delegated task where intermediate steps matter and you want progress, not one shot of text
- Coordinate multi-file office work (docs, sheets, slides) under approvals instead of copy-paste gymnastics in Chat
Work is not a free pass to unsupervised action on company systems. Approvals, review, and data rules still sit with you. Later posts in the ChatGPT Work tutorial track go deeper on first agentic tasks and checking results. Here you only need to recognize the mode and not waste it on a subject-line rewrite.
Where Work shows up (and why “available” is not “equal”)
As of writing, desktop Work is available more broadly than many people expect, including limited Free access for orientation. Web and mobile rollouts still vary by plan and region. Marketing lines may say you can open the door on every plan. Capacity is the constraint that bites. Free can be enough to learn the shape of Work. Day-to-day multi-step office work usually becomes practical on paid plans (Plus, Pro, Go where offered, Business, Enterprise) with higher usage budgets.
If your org uses Business or Enterprise, admin controls and workspace policy matter as much as the mode label. Folder access, connectors, and what counts as approved data are not personal taste. They are policy. When money or compliance is real, re-check OpenAI’s current plan matrix and your IT notes rather than a Slack rumor from last quarter.
Usage: Work burns more than Chat
Chat is usually the cheaper way to spend a limit: one prompt, one reply, a couple of follow-ups. Work spends more because multi-step agents take more tool calls, more context, and more “thinking” time. That is not a moral failing of the product. It is why Free feels generous for chat demos and tight for agent demos. Scope the job in one sentence before you start Work. Vague agent goals burn capacity while the model explores.
Codex: coding agent for repos, diffs, and PRs
Codex is the coding agent surface. It is for developers and technical professionals who live in software projects: repositories, diffs, tests, pull requests, and related developer workflows. As of writing, Codex is merged into the ChatGPT desktop app alongside Chat and Work, so you stop juggling a separate coding-only shell when the product has already combined them. Older Codex-only apps may still update into the combined desktop experience.
What Codex is good at
Point Codex at software work. Explore a repo. Propose multi-file edits. Read a failing test and try a fix under review. Draft a PR description that matches the actual diff. Review changes in a side panel when the product supports it. Work across projects when multi-repo flows are available. The important word is agent, not autocomplete. Autocomplete suggests the next few tokens while you type. An agent takes a goal, explores context, plans steps, and executes under guardrails. You still steer. You still review.
Codex is not only for people who write C++ for fun. Beginners who can open a project folder, read a diff, and run a test command can get value. You do not need to be the staff engineer who invented the monorepo. You do need enough judgment to say “that change is wrong” when the agent invents an API that does not exist.
What Codex is a bad default for
Do not open Codex for stakeholder emails, pure prose research, or a one-paragraph rewrite. You will get tooling noise and usage burn for a job Chat already does. Do not treat “I pasted code into Chat” as the same as “I used Codex.” Pasting snippets into Chat is coding with conversation. Codex is a different surface with repo context and developer workflows. Both can be useful. Call them by the right names.
Deep install, first project, and git-friendly habits live in the later ChatGPT Codex tutorial series. This map only needs you to know when to open the door and when to walk past it.
A chooser you can say in one breath
Ask three questions out loud before you switch modes:
- Is the main artifact language, or code? Language-first → Chat or Work. Code and repo-first → Codex.
- Is one careful conversation enough? If yes → Chat. If the job needs multi-step tool use and longer delegated progress in office work → Work. If engineering → Codex.
- Am I willing to review intermediate steps? If you need a 30-second subject line, stay in Chat. Agents shine when review is part of the job, not when you wanted faster autocomplete for one paragraph.
If you pick wrong, stop early. Copy the useful text out, open the right mode, and start clean rather than dragging a coding agent through a press-release rewrite.
Chooser table for real Mondays
Use this when a meeting gets fuzzy. Pick the row that matches the job, not the hype.
| Job you actually have | Default mode (as of writing) | Why |
|---|---|---|
| Draft, rewrite, explain, plan, Q&A in a thread | Chat (web, desktop, or mobile) | Conversation is the unit of work; low setup |
| Multi-step office work with apps, files, slides, sheets, docs | Work | Agent for knowledge work deliverables you still review |
| Explore a repo, edit files, run tests, open or review a PR | Codex | Coding agent with developer workflows |
| One short email from notes | Chat | Agent overhead is waste |
| Unclear, sensitive data, or high liability | Slow down: policy + Chat sandbox first | Do not grant folder or repo access by default |
| Ship model calls inside your own product | API / Platform (later map part) | Separate billing, keys, and engineering ownership |
Two people can share the same brand subscription and still need different doors for different hours of the day. An ops lead might live in Chat and Work. An engineer might live in Codex and only open Chat for prose. That is normal. Shared vocabulary beats shared habits.
Plans, Free limits, and “you can open it” language
As of writing, OpenAI markets Chat, Work, and Codex as available on desktop across a wide range of accounts, including Free for limited use. That can be true as a “you can open the doors” claim and still false as a “you get the same capacity” claim. Free is useful for orientation. Multi-step Work and Codex tend to burn usage faster and hit limits sooner. Plus, Pro, Go (where offered), Business, and Enterprise are where heavier Work and coding patterns usually become practical day to day.
Web and mobile Work rollouts still depend on plan and product stage. Do not assume every desktop button has a full twin on Free mobile. When SLA, legal, or budget is real, screenshot the plan page for your account type and date the note.
| Question | Practical answer |
|---|---|
| Can Free open desktop Chat? | Yes for normal ChatGPT login and download paths OpenAI documents. |
| Can Free touch Work or Codex? | Often yes as limited access; capacity is the constraint, not curiosity. |
| When should I pay? | When Chat limits or Work/Codex capacity block real weekly work, not because a banner shouted once. |
| Business / Enterprise? | Org admin, data controls, and workspace choice matter more than mode labels. Follow IT policy. |
| Why did my agent session die mid-task? | Usage and plan limits often hit multi-step modes first. Export what you have; do not re-run the whole loop blindly. |
Before you roll out a team habit, write three facts on one page: which modes each seat includes today, what data is banned from personal accounts, and who owns review for agent outputs. If you skip that page, you will learn the rules from a surprise limit wall or a compliance email.
Worked example: one launch phrase, three doors
Imagine a 30-minute standup. The product manager says, “Let’s use ChatGPT on the launch.” Without a map, four people walk away with four plans.
Alex (PM) opens Chat, pastes the brief, and asks for a timeline critique plus risks for sales. Correct door for that slice of work.
Sam (ops) opens Work, points at a set of meeting notes and an allowed folder of partner PDFs, and asks for a one-page risk table plus a first-pass status deck outline. Correct door if policy allows the files and tools involved.
Jordan (engineer) opens Codex against the repo, asks for a dark-mode toggle that matches existing patterns, reviews the diff, runs tests, opens a PR. Correct door.
Riley (data) starts pasting production customer IDs into Chat on a personal Free account because “it’s faster.” Wrong door, wrong account, wrong data. Riley should use approved tools, scrubbed samples, and whatever path IT named for sensitive work.
The phrase “use ChatGPT” was incomplete. The fixed version is longer and clearer: “Alex: Chat for the brief. Sam: Work for the partner pack if legal says yes. Jordan: Codex for the UI change. Riley: no customer IDs in personal Chat, full stop.” That sentence saves two days of crossed wires.
Habits that protect usage and sanity
- Scope agent jobs in one sentence before you start Work or Codex. “Make it better” is not a scope.
- Prefer Chat for the first draft of language, then only move to Work if the remaining work is truly multi-step.
- Do not open Codex for prose. Tooling noise and usage burn for a job Chat already does.
- Watch plan usage indicators when the product exposes them. If you hit a wall mid-task, export what you already have.
- On shared Business seats, heavy Work and Codex sessions can be a team cost, not a private hobby. Know your org’s norms.
- Review outcomes, not vibes. Diffs, numbers, names, and “did this touch the wrong folder?” still sit with you.
Common mistakes
Treating Work as “Chat that tries harder”
A longer Chat thread is still a conversation. Work is multi-step agent work with tools and deliverables under review. If your org allows Chat but restricts folder or app agents, those are different policy lines for a reason.
Treating Codex as “Chat that writes code”
You can paste code into Chat. Codex is still a different product shape: repo context, multi-file edits, PR workflows, developer surfaces. If you only ever paste snippets into Chat, you are coding with conversation. That can be fine. Call it what it is.
Assuming mobile has every desktop agent feature
Mobile is excellent for many Chat tasks and for checking progress when the product supports it. It is a weak place to invent your whole security model. Start policy from desktop and web realities, then layer mobile.
Burning agent capacity on tiny jobs
Subject lines, one-paragraph rewrites, and single definition lookups belong in Chat. Starting Work because it feels more “advanced” is a tax on your weekly limit and your review time.
Skipping verification because the product feels agentic
More steps completed by software does not mean more truth. It means more surface area to review. A polished deck outline with a wrong number is worse than a rough Chat draft that forced you to check the source sheet.
What stays the same across every mode
Maps can make products feel more different than they are. A few constants still hold wherever you click.
Models still predict under product limits. A prettier agent UI does not turn ChatGPT into a database of your private company facts. If the fact was not in the prompt, the files you attached, the tools you connected, or reliable retrieval your org built, treat detailed “memory of last quarter’s numbers” with suspicion until you verify.
Humans still own liability. Chat draft, Work deliverable, Codex PR: if it ships wrong, your name is still on the outcome. Agents increase speed and surface area. They do not absorb responsibility.
Data handling still matters. Personal Free and paid accounts, team seats, and enterprise controls are different trust boxes. Paste rules from Learn ChatGPT and from your IT policy still apply when you open Work or Codex. Folder access is not a free pass to drop payroll exports into a home laptop account.
Names still change. Model labels, plan bundles, and which seat includes which agent have moved multiple times. Date your notes. Prefer screenshots of the pricing and help pages over tribal knowledge from a Slack thread last spring.
FAQ: short answers you will need in meetings
Is Work “better ChatGPT”?
No. It is a different mode for multi-step office work. For writing a client email, Chat is usually better. For a multi-source brief with tools and deliverables, Work is usually better. “Better” only makes sense next to a job.
Do I need Codex if I already paste code into Chat?
Not always. Snippet pastes handle many small coding questions. Codex earns its keep when the job is multi-file work in a real project with diffs and PR habits. If your org has not approved coding agents, stay on Chat with scrubbed samples.
Is Free enough to learn the three modes?
Often yes for orientation on desktop. Capacity is tighter on Work and Codex. Learn the doors on Free if you can open them, then pay when weekly work hits a wall, not when a banner tells you to feel left out.
Should every teammate use every mode?
No. Start with Chat fluency. Add Work for people who run multi-step file and office workflows under policy. Add Codex for people who touch repositories. Unused agents still create permission questions and support load.
How to practice this week
- Write down the last three times someone said “ChatGPT” at work. Label each with a mode: Chat, Work, Codex, or unknown.
- Open chatgpt.com and, if you use it, the desktop app. Note which modes you actually see on your plan. Date the note.
- Pick one real task for tomorrow. Force yourself to choose a mode before you type. If you choose Chat, write one sentence on why Work or Codex would be worse for that task.
- If you have never used anything beyond Chat, stop after one careful Chat session this week. Do not start three agent experiments “just in case.”
- Skim OpenAI’s help and product pages for desktop and plan language so your team notes match current labels, not last year’s screenshots.
Where this series goes next
Part 2 is Custom GPTs vs plain chat: when a saved recipe beats restating context every time, and when a GPT is the wrong solution. Later map parts cover model names without hype and the API path for builders. Deep Work, Codex, and Custom GPT tutorials live in their own series after this map is clear.
If you still want everyday Chat habits before you expand modes, stay with Learn ChatGPT from scratch. For the Anthropic sibling map (chat vs Code vs Cowork), see Learn Claude from scratch and the Claude product map series. Paths also sit on Learn.
Quick recap
- One brand, three primary job modes: Chat, Work, Codex.
- Chat is conversation: write, plan, Q&A, turn-by-turn judgment.
- Work is agentic multi-step office work with apps, files, slides, sheets, and docs under review.
- Codex is the coding agent for repos, diffs, and PRs, merged into ChatGPT desktop with Chat and Work.
- Work and Codex burn usage faster than short Chat. Free can open doors; capacity is not equal.
- When someone says “use ChatGPT,” answer with a mode name, not a vibe.
Sources
Official product pages and help used for this map (re-check before purchase or policy; surfaces change):
- OpenAI ChatGPT product home: https://openai.com/chatgpt/
- ChatGPT app: https://chatgpt.com/
- ChatGPT download (desktop entry points): https://chatgpt.com/download/
- OpenAI Help Center: https://help.openai.com/
- OpenAI Help: ChatGPT plans and features (search current plan articles on help.openai.com for Free, Plus, Pro, Business, Enterprise language)
- Analytics Made Simple: Learn ChatGPT from scratch (foundation series before this map)
- Analytics Made Simple: Learn hub (related paths)
