←back to thread

68 points gregpr07 | 1 comments | | HN request time: 0.202s | source

Hey HN – Gregor & Magnus here again.

A few months ago, we launched Browser Use (https://news.ycombinator.com/item?id=43173378), which let LLMs perform tasks in the browser using natural language prompts. It was great for one-off tasks like booking flights or finding products—but we soon realized enterprises have somewhat different needs:

They typically have one workflow with dynamic variables (e.g., filling out a form and downloading a PDF) that they want to reliably run a million times without breaking. Pure LLM agents were slow, expensive, and unpredictable for these high-frequency tasks.

So we just started working on Workflow Use:

- You show the browser what to do (by manually recording steps; show don’t tell).

- An LLM converts these recordings into deterministic scripts with variables (scripts include AI steps as well, where it’s 100% agentic)

- Scripts run reliably, 10x faster, and ~90% cheaper than Browser Use.

- If a step breaks, workflow will fallback to Browser Use and agentically run the step. (This self-healing functionality is still very early.)

This project just kicked off, so lots of things will break, it’s definitely not production-ready yet, and plenty of stuff is still missing (like a solid editor and proper self-healing). But we wanted to share early, get feedback, and figure out what workflows you’d want to automate this way.

Try it out and let us know what you think!

Show context
ProofHouse ◴[] No.44010075[source]
Can utilizing Chrome Extensions be added? It seems no one has and would be a critical bridge to many browser tasks
replies(2): >>44010131 #>>44012089 #
1. casslin ◴[] No.44012089[source]
we built a chrome extension supporting browser use: https://github.com/nanobrowser/nanobrowser, feel free to implement workflow use on top of our code base in typescript. Love to learn how it works!