250xp

Basically it's about the quality of the code output and scenarios flexibility. Recorders that don't have any AI layer on top produce:

- Brittle selectors

- Dump entire scenario into a single file

- Do not allow any logic besides replaying your steps

Qure writes clean code with properly reusable abstractions like Page Object (or whatever do you have in your existing automation repository). For the team it means less flakiness and less time spent on maintenance

And if we consider AI-powered tools, they require much more steering from the human perspective: describing test in text, forcing agent to follow specific guidelines (e.g. for selectors), asking agent to refactor stuff after main scenario is working. Qure agent handles that out of the box itself

Building a dozen projects for myself if I cannot find anything suitable in 5h search (lang learning, shortcuts optimization, E2E web testing), perfecting until I'm ok with the result (perfectionist here, haha)

Suddenly, a few of them have some friend requests, and then it grows. Until I see the numbers that could change the way I work, it's just a help for like-minded people, who like using sthing that goes beyond "this is vibecoded MVP". At the same time I really like going beyond that MVP bar, which is kinda de facto standard rn. So it's just a hobby of creating something cool

Though costs are low for me — few subscriptions (Supabase, GH) and $50 on LLM calls

Btw, why are you asking?