Anything API - Any website. We deliver the API.

The "any website to API" framing sells this short. What you're actually building is the execution layer for browser agents at scale, and that's a much bigger deal. Every team building browser-based agents hits the same wall: the browser is the messiest, most unpredictable environment for agents to operate in, and making that reliable enough for production is genuinely hard.

Curious Kitty's question about session persistence and MFA is the real challenge. Browser automation that works in demos falls apart in production when you hit auth flows, CAPTCHAs, rate limits, and all the other real-world friction. The fact that you're building on the full Notte ecosystem for browser profiles and vaults suggests you're thinking about this the right way. How are you handling failures when a site changes its DOM structure mid-workflow?

Really interesting approach. One challenge I’ve seen with agent-based automation is that reliability often breaks once multiple external services are involved.

Curious if you’ve seen cases where the generated endpoint works initially but starts failing later due to subtle changes in the target site or upstream services.

Hey guys
really cool stuff and beautiful design. I really could use this for an upcoming project, but need either open source to host on the client or a managed api that could do this via api. Are you guys doing api for anything api? couldn't find in the platform.

Very cool. A few of the sources we pull from don’t expose APIs, so we’ve had to rely on makeshift solutions. Can see this being super useful!

This is solving a real pain point — we spent weeks building custom scrapers for supplier portals when prototyping bill.dock.io, and half of them broke within a month. The "any website" promise is bold; I'm curious how you handle sites with aggressive bot detection or login-gated content that requires session persistence. What's your current success rate on authenticated enterprise portals specifically?

Lovely interface. I knew exactly what to do after reading : Describe the task, We engineer it, No agent improvising.

The product itself did not work for me, after trying it twice for the same task. The task I tried was : to download all of the images from an architect's design "portfolio" page, and to structure the information into a JSON - asking for description, type of building, number of rooms, etc. All of that information is on the page, but it currently exists as a description or an image.

It was unable to translate the information from the page into a different format, something that AI models are able to do. This is something we have to do at scale so having a tool like this would be useful for us.

Regardless of it not working today, I see the vision. Feel free to contact me if you want direct feedback. Good luck!

What does this do? For example, I enter the Amazon link and you give me all the APIs? Then I could pass that to my Claude Code to integrate them into my website? Is that how it works?

Looks pretty slick tbh. Been playing around with browser automation stuff lately and it’s usually either super brittle or way too complex to scale. Kinda like the idea of mixing deterministic scripts + AI, feels like that’s where things are going anyway. Curious how stable it actually is in prod tho, especially with sessions/proxies (that’s usually where things break at the worst moment).

If this actually works as advertised, could be huge for scraping, testing and even growth stuff. Definitely gonna keep an eye on this!

AgentFallback sounds clever but I'm trying to understand the cost model at scale. If you're running thousands of daily automations and each AgentFallback invocation triggers an LLM call, the economics could get tricky fast. Is there any reporting on how often the fallback actually fires in production, and is it priced separately or bundled?