Set up ChatGPT and Claude

What you'll walk away with: working accounts in both ChatGPT and Claude, the model picker found and left alone, the same first prompt answered in each — and the one distinction every lesson after this one leans on: the app is not the model.

You need: an email address, your phone (one of the sign-ups sends a text-message code), and about 20 minutes. Free tiers cover it. Nothing to install, no card.

Where you're standing

In late 2022 a website appeared with a text box. You type ordinary English into it — a question, a half-formed idea, a pile of notes — and a written answer types itself back, usually a good one, in seconds. Your industry has not stopped talking about it since, because so much professional work is exactly this: drafts, summaries, restructured notes, first-pass analyses.

You have heard the names — ChatGPT, Claude, Gemini, Copilot — and that it makes things up, that one firm banned it and another now requires it. All of that is true at once, and none of it tells you what the thing is.

The game board

Three companies matter most here. OpenAI makes ChatGPT. Anthropic makes Claude. Google makes Gemini. The lessons on this path, and the labs after them (real work on your own material), use the first two. Gemini is real and good, we simply don't cover it; everything you learn transfers. Copilot, if your company lives in Microsoft, is Microsoft's interface inside Word and Excel, with the same kind of engines under it.

Now the distinction: each product is two things under one name. There is the app — the website with the text box, the chat history, the folders, the settings. Inside the app there is a model — the machine that actually writes. The app is ordinary software, built by people, changed weekly. The model is the strange part.

One more fact, because the first dropdown you will meet is this one: each company makes a family of models — larger ones that reason more deeply and cost more to run, smaller ones that answer faster and cheaper, others tuned toward code, writing, or images. So "which AI is best" has no standing answer; it depends on at what, and on when you ask.

Hold onto the split: when something remembers your name across visits, that is the app; when something writes a paragraph, that is the model. The next lesson is about the model, and the window through which the app feeds it everything it gets. Today is about the app.

Why both

Because the products keep arriving at the same ideas under different names, fluency in both lets you read any tutorial, any colleague's setup, any announcement. And a fresh chat is a second opinion, best taken across two different engines — lesson 05, Managing chats, makes that a habit.

This site will not tell you which of the two to prefer, not today, not later. That answer is yours to earn; you start earning it today.

What today costs

Nothing, honestly arrived at, with asterisks stated now, before you rely on the free tiers. Claude's free tier meters messages in rolling periods of a few hours — if it pauses you, that is the meter, not a malfunction; finish later. ChatGPT's free tier meters differently: shifting limits, past which everyday chat quietly continues on a smaller engine. And parts of each app have drifted in and out of the paid tiers on both sides — none you need today.

Both sign-ups offer a paid plan. Decline everything today. The paid tiers mostly buy longer meters and earlier, longer access to the newest engines — decide after a week of experience, not on a landing page.

Do this in ChatGPT and Claude

Go to chatgpt.com and claude.ai and make an account on each — email or single-sign-on, decline every upgrade screen, and expect the text-message code on the Claude side. Put the two tabs side by side.

First, a ten-second look in either tab: click the model dropdown at the top of the chat. That is the family from the game board, under this season's names — the control that decides which engine reads your window. Leave it on the default; knowing it exists is today's whole job with it. One honest note: menus and sign-up screens move; if a step is not where this says, look for the nearest thing.

Then send the same first message in each tab, so both engines have written for you before you read another word about them:

In one short paragraph, tell me what you can help me with at work — then ask me one question about my job that would change your answer.

Read the two replies side by side. Do not decide anything yet; notice only that both answered fluently, and that the question each asked is the first hint of what a window is for. Keep both tabs open — every lesson from here runs in them.

What you'll see when you log in

Both products share a floor plan: six fixtures that anchor every menu you will open in either one, each about the same finite window — what goes in, or which engine reads it. Here they are on one card, named by job rather than label, with the lesson that hands you each:

• Chats — each one a fresh window with nothing of yours in it yet; the list down the left is history, not memory. Lesson 05.
• The model picker — the dropdown you just opened: which engine reads your window. The decoder keeps the current names, dated.
• A scoped workspace — files and standing instructions that brief every chat inside it. Lesson 11.
• Notes the app keeps about you between chats, loaded into the window for you. Lesson 12.
• An editable document beside the chat that you revise in place instead of re-prompting. Lesson 13.
• Connections to your other tools — what those tools hold, turned into text the window can read. Lesson 14.

---

Check your understanding: which company makes which product — and what is the difference between an app and a model? Say both before you open the answer.

Check yourself first — then open one good answer+−

OpenAI makes ChatGPT; Anthropic makes Claude; Google makes Gemini. And the app is the ordinary software around the text box — history, settings, folders — while the model is the machine that writes.

Your answer should have hit all three maker–product pairs and app versus model.

Use this setup in every lesson that follows. The next lesson, What happens when you press send, shows you the machine behind each tab.

Remember that product terms change. Every vendor name on this page is accurate as of August 2026, and at least one of them will be wrong before this sentence feels old; both companies rename and repackage constantly. When a name changes, the decoder is what gets corrected — so trust the job the fixture does, not the label on the button. For any other word either product hands you, the AI glossary defines 296 of them in plain English.