Visible Amsterdam: Join us Sep 3
Promptwatch Logo

ChatGPT agent

Agent that can use its own browser to perform tasks for user.
OpenAI
AI AssistantAgentUser Initiated

What is ChatGPT agent?

ChatGPT agent is OpenAI's AI agent. Agent that can use its own browser to perform tasks for user.

ChatGPT agent acts on behalf of a person rather than indexing the web in bulk. It arrives when someone asks it to complete a task on your site, so the pages and flows it can reach decide whether that task succeeds. Blocking it will not remove you from AI answers, but it can stop real people from finishing real actions.

Tracking which AI crawlers and agents reach your site, and what they do once there, is the foundation of generative engine optimization. See our guides to AI crawlers and robots.txt to control automated access and protect your AI search visibility.

Want to see every AI bot hitting your site? Promptwatch turns your server and CDN logs into a live view of AI crawler and agent traffic, so you can watch ChatGPT, Claude, Perplexity, Gemini, and others crawl your pages and connect those visits to real citations and revenue. Learn more in AI crawler logs.

See every AI bot hitting your site

Promptwatch turns your server and CDN logs into a live view of AI crawler and agent traffic. Watch ChatGPT, Claude, Perplexity, Gemini, and more crawl your pages in real time, see exactly what they take, and connect every crawl to the citations and revenue it drives.

How to handle ChatGPT agent

Most sites keep ChatGPT agent allowed, because it shows up when a real person asks it to do something on their behalf. Block it only if you do not want automated agents acting on your site.

ChatGPT agent does not send a stable user-agent token, so a robots.txt rule cannot reliably target it. It instead signs every request using Web Bot Auth HTTP message signatures and publishes its public keys at https://chatgpt.com/.well-known/http-message-signatures-directory. Verify that signature at your CDN or edge and allow or block it there.

OpenAI does not publish a robots.txt commitment for ChatGPT agent, so confirm how it behaves by watching your access logs.

Examples

  • A customer sends ChatGPT agent to complete a task on a site, and the operations team confirms the agent reached the pages it needed.
  • An engineer verifies ChatGPT agent against its published signature keys before allowing it through the edge.

Related bots

ChatGPT-User

Handles user-initiated requests in ChatGPT, accessing external content to provide real-time information; not used for automated crawling or AI training.

AI Assistant

GPTBot

Crawls web content to improve OpenAI's generative AI models and ChatGPT; respects 'robots.txt' directives to exclude sites from training data.

AI Crawler

OAI-AdsBot

Validates the safety of web pages submitted as ads on ChatGPT; data collected is not used to train generative AI foundation models.

Advertising

OAI-SearchBot

Indexes websites for inclusion in ChatGPT's search results; does not crawl content for AI model training.

AI Assistant

Amazon Kendra

Amazon Kendra is a managed information retrieval and intelligent search service that uses natural language processing and advanced deep learning model.

AI Assistant

Frequently asked questions about ChatGPT agent

Learn about AI visibility monitoring and how Promptwatch helps your brand succeed in AI search.

ChatGPT agent is operated by OpenAI. It functions as OpenAI's AI agent.

Be the brand AI recommends

Monitor your brand's visibility across ChatGPT, Claude, Perplexity, and Gemini. Get actionable insights and create content that gets cited by AI search engines.

Promptwatch Dashboard