Just a brief recap: people use Skyvern to automate the repetitive browser work nobody wants to do: pulling invoices from vendor portals, filling out healthcare forms, extracting data from sites that don’t have APIs. You can try it out here: https://github.com/Skyvern-AI/Skyvern
We’ve been using
Why wouldn’t people use different intelligences to create, vs test, code??
Using one’s own intelligence to create it, then using LLM to challenge it to find bugs,
XOR using 1 LLM to create it, then using another to challenge it, to find bugs…
NEVER have the same mind create a work, then try to find mental-errors in it: the mind-blindness hasn’t changed, so why would it see the problems??
_ /\ _