This is a super interesting product, guys. I get that agents aren't great for everything right now, but I'd expect that they'll continue to improve over time (like everything in the LLM space).

How do you see the product evolving as agents become better and better?

Thanks, and great question - we think about this a lot and think there are a couple of things here.

First, as models get better, our agent's ability to navigate a website and generate accurate automation scripts will improve, giving us the ability to more confidently perform multi-step generations and get better at one-shotting automations.

We expect browser agents will improve as well, which I think is more along the lines of what you're asking. At scale, we still think scripts will be better for their cost, performance, and debuggability aspects - but there are places where we think browser agents could potentially fit as an add-on to deterministic workflows (e.g., handling inconsistent elements like pop-ups or modals). That said, if we do end up introducing a browser agent in the execution runtime, we want to be very opinionated about how it can be used, since our product is primarily focused on deterministic scripting.

Agents have plateaued and will never be as good as deterministic code for browser automation. It's a fundamental issue with the way LLMs work.