What it does
Ask Claude in a chat and it writes, tests and debugs code, and analyzes code you share with it. It can also run code and create files for you.
Checked 2026-11-14 · Source · Source 2Good for you if…
- You want help with code without installing developer tools: it works in the browser and in the desktop and mobile apps
- You want to start for free: the free plan lets you ask for code, with usage limits that reset every 5 hours and every week
- You already use Claude for other work and want code help in the same place; Pro also includes Claude Code for bigger coding jobs
Think twice if…
- You want an AI to edit files and run commands inside your project for you: that’s Claude Code, Anthropic’s separate coding tool, which the free plan doesn’t include
- You don’t want your code used for training: on personal plans it can be, unless you turn it off in settings
- You need heavy, all-day use for free: the free plan’s usage is limited
How to start
- Go to claude.com and sign up for free with your email. Prefer an app? Get the desktop or mobile app at claude.com/download.
- Say what the code should do and which programming language you use, or paste in the code you want fixed or explained.
- Copy the code it gives you into your project and try it. If you get an error, paste the error message back into the chat.
- Ask for changes in plain words until it does what you need. For bigger jobs inside your project, look at Claude Code, which comes with Pro.
Will it train AI on my code?
On personal plans it can, unless you turn it off: while the “Help Improve our AI models” setting is on, Anthropic uses your chats, including code you paste in, to train new models. Anthropic’s terms describe this as opt-out, and new users choose the setting when they sign up. To turn it off, go to Settings › Privacy and switch off “Help Improve our AI models”. Even then, chats you give feedback on (thumbs up or down) and chats flagged for safety review can still be used; incognito chats aren’t used to improve Claude. On Team and Enterprise plans, Anthropic’s Commercial Terms say it may not train models on your content.
Applies to Claude on the web, desktop and mobile apps, sending your chats to Anthropic’s own Claude models. Free, Pro, Max and Ultra follow Anthropic’s Consumer Terms; Team and Enterprise follow its Commercial Terms. Other ways of reaching Claude models (the API, cloud providers) are not checked here.
We may use Materials to provide, maintain, and improve the Services and to develop other products and services, including training our models, unless you opt out of training through your account settings.We will train new models using data from Free, Pro, Max, and Ultra accounts when this setting is on (including when you use Claude Code from these accounts).
Source 2If you’re a new user, you can pick your setting for model training during the signup process.
Source 3Under Help Improve our AI models, click the button to toggle it off/on
Source 4Your Incognito chats are not used to improve Claude, even if you have enabled Model Improvement in your Privacy Settings.
Source 5We may use your feedback to analyze the effectiveness of our Services, conduct research, study user behavior, and train our AI models as permitted under applicable laws.
Source 6Commercial Terms of Service (for Team, Enterprise, and API users)
Source 7Anthropic may not train models on Customer Content from Services.
Source 8
Summary of the maker’s terms as checked on 2026-11-14. Always read the official terms; this is not legal advice.
