---
title: Our reader
description: The reader that fetches the public sources, and how it identifies itself.
canonical: https://welila.com/bot
---

# Our reader

The reader fetches the sources an assistant would, identifies itself, and signs what it sends.

To check a business's facts, Welila reads the same public sources an assistant would: the website, the search listings and the directories. The reader that does this identifies itself, honours the rules a site publishes, and holds to a polite rate.

## How it identifies itself

- It sends a user agent that names Welila and links back to this page.
- It signs its requests, so a site can verify the request came from Welila and not from something wearing its name.
- It honours robots and crawl-delay, and holds one request a second per host.

## The assistants Welila reads for

Welila serves the assistants people actually ask: ChatGPT, Claude, Perplexity, Google and Bing. The robots policy allows the readers those operators publish and refuses the two bulk scrapers that train without reading for a person.

## If you run a site

You do not have to do anything. The reader takes what is public and takes it gently. If you want it to slow down or stop, publish the rule and it is honoured, and you can write to hello@welila.com.