What is an agentic browser?
An agentic browser is a web browser, or a mode of one, in which an AI agent works through pages on a person's behalf: it opens tabs, clicks, fills in forms and adds products to the cart to finish a task. An agentic browser differs from an assistant that only summarizes the page it sits on, and it usually asks for confirmation before paying.
Key takeaways
- An agentic browser does not just read the page: it uses it, with clicks and forms, to finish a task a person gave it.
- Google launched auto browse in Chrome on January 28, 2026 for subscribers in the United States, and brought it to Android in August 2026.
- OpenAI announced in July 2026 that it was retiring its Atlas browser, with the shutdown set for August 9, and moved those features into ChatGPT and its desktop app.
- Agents that browse from the cloud can sign their requests, as the ChatGPT Work browser does with Web Bot Auth.
- Vendors ask for confirmation before paying and admit that these agents can fall for instructions hidden in a page.
An agentic browser is not a browser with a chat in the sidebar that summarizes the page for you. It is one where an AI agent takes the controls: it opens your store, picks a size, applies a discount code and gets as far as the cart because someone asked it to. For a merchant, that changes who walks the product page. It is no longer just a person reading or a crawler downloading the HTML: it is a program that uses the page the way a customer would, and it gets stuck where a hurried, impatient shopper would get stuck.
How it works
The agent looks at the page, decides the next step and carries it out in the browser: a click, a field it fills in, a new tab. Vendors describe their products with tasks like these. What changes from one to the next is where the browser runs and how much it is allowed to do.
Google, inside Chrome. On January 28, 2026, Google introduced auto browse, a Gemini feature in Chrome that handles multistep tasks on the user's behalf. Its examples include comparing hotels and flights, filling in forms and, starting from a photo, finding similar items, adding them to the cart without going over budget and applying discount codes. With permission, it uses Google Password Manager to sign in. It is in preview for Google AI Pro and AI Ultra subscribers in the United States, and Google announced that Chrome will support the UCP (Universal Commerce Protocol).[1]Google, official blog (Parisa Tabriz). The new era of browsing: Putting Gemini to work in Chrome On August 18, 2026 it reached Android, again for those subscribers in the United States.[2]Google, official blog (Charmaine Dsilva). Gemini in Chrome on Android, with auto browse
OpenAI, first in its own browser and then in ChatGPT. OpenAI launched ChatGPT Atlas on October 21, 2025, a browser with ChatGPT built in and an agent mode in preview that could, for example, look up a grocery store, add a recipe's ingredients to the cart and place the order.[3]OpenAI. Introducing ChatGPT Atlas On July 9, 2026 it announced the browser's retirement, with the shutdown set for August 9, 2026: the agent features moved to ChatGPT and Codex, and for longer browser work it pointed people to the desktop app.[4]OpenAI, Help Center. ChatGPT release notes Since August 25, 2026, the ChatGPT Work browser can complete tasks on sites that require sign-in, and it asks for confirmation before actions such as a booking or a payment.[4]OpenAI, Help Center. ChatGPT release notes
Where it runs matters to your server. An agent can work in the user's own browser or in a cloud browser run by the provider. The ChatGPT Work cloud browser signs every request with the HTTP Message Signatures standard (RFC 9421), with a Signature-Agent header set to "https://chatgpt.com", and OpenAI publishes the keys to verify it. Cloudflare recognizes it as a signed agent in its bot directory.[5]OpenAI, Help Center. ChatGPT Work's Cloud browser allowlisting That is the Web Bot Auth method, and it is what lets you tell a legitimate agent from one that only copies its name.
Pages are starting to talk to agents. Today an agent acts on the interface, pressing what it sees. In February 2026 Chrome proposed WebMCP, a standard way for a website to expose structured tools: a declarative API over HTML forms and an imperative one with JavaScript. Its commerce example is an agent that finds the products, configures the options and walks through the checkout with precision. It is in preview for enrolled participants.[6]Chrome for Developers (André Cipriani Bandarra). WebMCP is available for early preview Since August 31, 2026, ChatGPT Work and Codex use those tools in the desktop app's built-in browser, on compatible sites.[4]OpenAI, Help Center. ChatGPT release notes
In a store
A request like "buy me trail running shoes in size 10 for under $130" turns into steps on your site. It is a made-up example, to see what the agent needs at each one:
| Agent step | What it has to find in your store |
|---|---|
| Reaches the product page | Name, price and availability written on the page, not only in an image |
| Picks the size | A variant selector with sizes as text and the sold-out ones marked |
| Checks the total | Shipping costs and delivery time visible before payment |
| Applies a discount | A code field that works without hidden steps |
| Reaches payment | A checkout that does not block it for looking automated |
At the last step the vendors stop: auto browse is designed to ask for confirmation before completing a purchase,[1]Google, official blog (Parisa Tabriz). The new era of browsing: Putting Gemini to work in Chrome and ChatGPT Work asks before consequential actions such as a payment.[4]OpenAI, Help Center. ChatGPT release notes The agent prepares the purchase; the person confirms it. There is a second reason for that pause: OpenAI acknowledges that an agent can fall for malicious instructions hidden in a page or an email, meant to make it do something the user did not ask for, and that its defenses will not stop every attack.[3]OpenAI. Introducing ChatGPT Atlas Google says it trains its models to detect known threats such as this prompt injection.[2]Google, official blog (Charmaine Dsilva). Gemini in Chrome on Android, with auto browse When the agent can buy without leaving the conversation, the term is agentic checkout.
What people often get wrong
Believing that an agentic browser is just another crawler and is controlled the same way. A crawler walks the web on its own; an agentic browser goes where a person sends it. The rules in robots.txt were designed for the first: OpenAI, for example, warns that robots.txt rules may not apply to visits a user initiates from ChatGPT.[7]OpenAI. Overview of OpenAI Crawlers And blocking an agent of this kind is not stopping a training bot: it is turning away a customer who has sent someone to buy.
How to check it
- Make the request yourself. Ask an agent to find a product in your store, pick a variant and get to the cart, and stop it before payment. Write down where it hesitates or gets it wrong.
- Review your bot protection. If you use a CDN or a firewall, see how it treats signed agents: the ChatGPT Work browser can be verified by its signature, and Cloudflare, Akamai and HUMAN recognize it.[5]OpenAI, Help Center. ChatGPT Work's Cloud browser allowlisting
- Look for the signature in your logs. Requests from the ChatGPT Work cloud browser carry the
Signature,Signature-InputandSignature-Agentheaders.[5]OpenAI, Help Center. ChatGPT Work's Cloud browser allowlisting - Read your product page without images. If the price, the sizes or the shipping costs only make sense by looking at a photo, an agent has a harder time than a person.
- Follow WebMCP if you develop your store. It is a proposal in preview: worth trying, not worth depending on yet.[6]Chrome for Developers (André Cipriani Bandarra). WebMCP is available for early preview
Related concept: AI agent
The AI agent is the one that decides; the agentic browser is one of the hands it acts with. The same agent can work with a browser, call the tools a site exposes or talk to a store through a commerce protocol, without opening a single page. For merchants, the agentic browser is the path that requires no integration: it uses the store as it is, with its strengths and its snags. Protocols like UCP and the product feed are the structured path, and agentic commerce brings them all together.
To go further, the agentic commerce reading path orders the rest of the terms, and the ChatGPT product feed explains OpenAI's structured path.
Synonyms
- English
- agentic browser, AI browser agent
- Español
- navegador con agente, navegador con IA
Sources
- [1] Google, official blog (Parisa Tabriz). The new era of browsing: Putting Gemini to work in Chrome. Accessed . ↑ ↑
- [2] Google, official blog (Charmaine Dsilva). Gemini in Chrome on Android, with auto browse. Accessed . ↑ ↑
- [3] OpenAI. Introducing ChatGPT Atlas. Accessed . ↑ ↑
- [4] OpenAI, Help Center. ChatGPT release notes. Accessed . ↑ ↑ ↑ ↑
- [5] OpenAI, Help Center. ChatGPT Work's Cloud browser allowlisting. Accessed . ↑ ↑ ↑
- [6] Chrome for Developers (André Cipriani Bandarra). WebMCP is available for early preview. Accessed . ↑ ↑
- [7] OpenAI. Overview of OpenAI Crawlers. Accessed . ↑
Change history
- First English version.
This definition is published under CC BY 4.0. Reuse this definition freely, crediting Clione with a link to this page.
Related terms
AI agent
What an AI agent is according to OpenAI and Anthropic, how it differs from a chatbot or a fixed workflow, and what it needs from a store to buy.
Agentic checkout
What agentic checkout is, when an AI agent pays for the shopper, how ChatGPT, Google and Shopify do it and what your store needs to have ready.
Agentic commerce
What agentic commerce is, how discovering, recommending and buying separate, and what works today in ChatGPT and Google versus what is only announced.
Web Bot Auth
What Web Bot Auth is, the IETF draft for bots and AI agents to sign their HTTP requests, who already uses it and how a signature is verified.
UCP
What UCP (Universal Commerce Protocol) is, how a store publishes its capabilities at /.well-known/ucp, and what works today in AI Mode and Gemini.
ChatGPT product feed
What the ChatGPT product feed is, which fields OpenAI requires, how to send it by SFTP or API, which markets it covers today and how to validate it.
Make your catalog easy for bots to read
Clione fills every product page with what bots read best: the JSON-LD graph with its structured data, the meta description and the FAQs. You review and press Push; then we check your live store so it all stays published.