Does your message sound like a bot wrote it?

Paste an email, a text or a post. Everything a reader would hold against it gets marked, with what to write instead. It runs in your browser: nothing you paste leaves this page.

Try
0 words

What a reader would notice

Nothing yet.

Not an AI detector

bot-tells cannot tell who wrote a message, and does not try. People write every one of these phrases too. It finds the things a reader would hold against the message, whoever wrote it.

A leak, such as a [First Name] nobody filled or a "Here's a draft:" left at the top, fails the message outright. Tells only add to the score.

For agents and pipelines

The same checks as a CLI, a library and an MCP server, so an agent can check its own writing before it sends anything.

npx @askeleven/bot-tells draft.txt
claude mcp add bot-tells -- npx -y @askeleven/bot-tells mcp