suchintan

This is very cool! How do you guys compare to the incumbents like Webflow and Framer?

We wrote something like this to power Skyvern: https://github.com/Skyvern-AI/skyvern/blob/0d39e62df6c516e0a... It's adapted from vimium and works like a charm. Dis…

I suspect accuracy is going to vary between domains that LLMs are being applied to Interesting call about validating this against YAML / TOML / CSV / HCL. HTML was natural for us becaus…

I've been using briefer for the past few weeks and have a few questions: 1. Do you intend Briefer to be a jupyter replacement or a metabase replacement? 2. Do you have any plans to open source br…

I love love love this idea! The papers all look like they're from April? Any chance to get more recent stuff?

https://github.com/Skyvern-AI/skyvern This is pretty much what we're building at Skyvern. The only problem is that inference cost is still a little bit too high for scraping…

I think there are some they're good enough at today. Auto generating meeting notes + AI context, auto responding / following up to emails, filling out forms (we do that pretty well at Skyver…

I don't think ai agents are good enough to replace every job today, but they're starting to nip at the more junior / menial knowledge jobs I've seen a lot of success come from AI s…

We're definitely planning this. Skyvern currently intercepts all network calls that gets made -- we save them all as a HAR file for debugging purposes... but never looks at them A lot lot lot of …

We've discussed generating automation code internally a bunch, and what we decided on is to do action generation and memorization, instead of code generation and memorization. They're not th…

What do you mean? All of our code can be found here https://github.com/Skyvern-AI/Skyvern

Imagine that exact use-case -- pulling up relevant tax information and filling it Now imagine it from the accountant POV, where they have the same use-case for hundreds of clients This is where we…

This is a great point. This is something already on our roadmap. We call it "prompt caching", but I realize writing this that it's a terrible name. Will update! ( https://gith…

Interesting. We've decoupled navigation and extraction for specifically this reason, but I suppose decoupling selector with input could let us use cheaper smaller LLMs to "select" and a…

We're gonna build a self-serve UI soon! We just wanted to get it into people's hands ASAP :) Feel free to email me at suchintan@skyvern.com -- I can let you know when the self-serve UI is li…

This can definitely be used for front end testing. Just tell it to do something like a user and monitor whether it's successful or not Here's a prompt example to try out { "url": &…

Actually this kind of stuff is super exciting -- we don't need to depend on companies exposing APIs for their website -- we can just use something like Skyvern instead!

When you say "getting the data in the client's infrastructure", do you mean self-hosting the robots? or something else?

We DEFINITELY will. I think we're planning on pushing that next week -- we've been super excited about it Just created this: https://github.com/Skyvern-AI/skyvern/i…

Nice! Thanks for sharing this. We tried approaches like VimGPT before but found the rate of hallucinations to be a bit too high to be used in production. The sweet spot definitely seems to be to combi…

We're quite different than LaVague. LaVague passes in the entire HTML DOM to the LLM to help it generate XPaths and valid Selenium code. ( https://github.com/lavague-ai/LaVagu…

Thanks! We definitely experimented with V only (that's the dream), but there's too much context missing: 1. What's behind a select option? You don't know until you click it, which …

Saw the launch yesteday. Love all of the excitement in the space! LaVague is all about generating selenium code to interact with a specific page, and do it step-by-step Skyvern is all about taking a s…

https://github.com/Skyvern-AI/Skyvern/?tab=readme-ov-file#fe... …

I love all of these ideas!! 1. You can set a "max steps" limit when you run it locally https://github.com/Skyvern-AI/skyvern/blob/d0935755963b017ed... We also…