← Back to context

Comment by hannob

6 months ago

Okay, maybe this is a stupid question, but: what is an agentic browser? You seem to assume that everyone knows what that means.

Is this a common and well-defined term that people use? I've never heard it.

It would appear to me from the context that it means something like "web browser with AI stuff tackled on".

18 comments

hannob

Reply
felarof  6 months ago

Thanks for asking - not a stupid question at all! I should have probably explained it at the top of my post.

By "agentic browser" we basically mean a browser with AI agents that can do web navigation tasks for you. So instead of you manually clicking around to reorder something on Amazon or fill out forms, the AI agent can actually navigate the site and do those tasks.

  • wild_egg  6 months ago

    Not to pull a "why should I use Dropbox when I have rsync" but why should we use this over adding a Playwright MCP to Claude Desktop or similar?

    Does having access to Chromium internals give you any super powers over connecting over the Chrome Devtools Protocol?

    • felarof  6 months ago

      Yes, eventually we think there is more value of owning the entire stack than just be a MCP connector.

      Few ideas we were thinking of: integrating a small LLM, building MCP store into browser, building a more AI friendly DOM, etc.

      Even today, we use chrome's accessibility tree (a better representation of DOM for LLMs) which is not exposed via chrome extension APIs.

      5 replies →

kordlessagain  6 months ago

Agents are LLM responses that are feed with tools, like calculate(expression). When it encounters a thing it needs to do to meet desired output, it will run the tool. That is defining a simple agentic workflow.

A complicated workflow may involve other tools. For example, the input to the LLM may produce something that tells it to set the user-agent to such and such as string:

  set_user_agent("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36");

Other tools could be clicking on things in the page, or even injecting custom JavaScript when a page loads.

al_borland  6 months ago

I first heard the term agentic about a month ago. I went from never hearing it, to hearing it 3 or 4 times in 2 days... one of which was on an internal town hall where I work, where leadership was simply using it as if the whole world already knew what it meant, instead of literally being the first time it was ever mentioned.

The tl;dr is that it's AI that makes decisions on its own.