keremyilmaz

Ah, now that makes sense! Thanks for sharing it. We definitely didn’t have that in mind when naming it Skyvern, but it's cool to see how it could be interpreted that way

I was so surprised to read this, especially since we definitely didn't know about it when naming Skyvern.

Out of curiosity, I checked both Cambridge's Norwegian-English dictionary and a few other Norwegian sources, but I couldn't find 'Skyvern' listed anywhere. Makes me wonder if Google translate just hallucinated the meaning.

You've raised valid points about the cost and efficiency of our approach, which aims to make the LLM function as closely as possible to a human user. We chose this approach primarily for its compatibility with various websites, as it aligns closely with a website's intended audience, which is typically human.

Addressing complex website interactions is a key advantage of this approach. For instance, in the process of generating an auto insurance quote, the sequence of questions and their specifics can vary greatly depending on prior responses. A simple example is the choice of a foreign versus a California driver's license. Selecting a foreign license triggers additional queries about the country of issuance and expiry date, illustrating the complexity and branching nature of such web interactions.

However, we recognize the concerns about cost and are actively working on strategies to reduce it: - Optimizing the context provided to the LLM - Implementing caching mechanisms for certain repeated actions and only use LLMs when there's a problem - Anticipating advancements in LLM efficiency and cost-effectiveness, with the hope of eventually finetuning our own models for greater efficiency

Skyvern is actually an API-first product! The UI we built is mainly for simplicity and being able to debug the steps our agent takes.

You can easily copy sample curl requests through our UI. Feel free to check out the quickstart on our GitHub and let us know if you have any questions.

Just got a cool idea! Would it be possible to implement a GH workflow that works only when there is a workflow failure in the PR, and explains what could be the issue/how to solve it?