Claude

Draft a document with Claude and ask it to revise the next pass.

Anthropic•Write & polish•Earliest fact checked 2026-11-14
Get started Official site We only link to official sites.

Good for: Expand an outline into a draft

Not for: You need all citations independently verified

What it does

Draft a document with Claude and ask it to revise the next pass.

Checked 2026-11-15 · Source

Good for you if…

  • Expand an outline into a draft
  • Revise a brief after feedback

Think twice if…

  • You need all citations independently verified
  • Your recipient requires formal approval in a separate document system

How to start

  1. Open the official tool or its setup page.
  2. Give Claude an outline and ask it to create a draft document.
  3. Request a revision and check that facts and intent are preserved.

Will it train AI on my content?

Anthropic may use personal chats to train models when “Help Improve our AI models” is enabled. New users choose this setting during signup. To turn it off, go to Settings › Privacy. Feedback and chats flagged for safety review are exceptions under the consumer terms. Incognito chats aren’t used to improve Claude. Team and Enterprise are covered by the Commercial Terms, which prohibit training on customer content.

Applies to Claude on the web, desktop and mobile. Free, Pro, Max and Ultra follow the Consumer Terms; Team and Enterprise follow the Commercial Terms.

From the official terms
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 2
  • If you’re a new user, you can pick your setting for model training during the signup process. Source 3
  • Under Help Improve our AI models, click the button to toggle it off/on Source 4
  • Your Incognito chats are not used to improve Claude, even if you have enabled Model Improvement in your Privacy Settings. Source 5
  • We 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 6
  • Commercial Terms of Service (for Team, Enterprise, and API users) Source 7
  • Anthropic may not train models on Customer Content from Services. Source 8
Checked 2026-11-14 · Source · Source 2 · Source 3 · Source 4 · Source 5 · Source 6 · Source 7 · Source 8

Summary of the maker’s terms as checked on 2026-11-14. Always read the official terms; this is not legal advice.