canergl

cool project but, It's not always code that's broken. Imagine you have a discrepancy in DB level that ends up with an error in frontend.

You always need real QA tests to ensure things are working smoothly.

can you share with us if It's public?

yes, It uses gemini vision models on top of playwright

Argus adds one more layer onto Playwright, so we expect it to be slower. Think of it as a kind of tradeoff where you gain human-level QA by accepting slower runs.

2 red flags

1- no comparison with gemini 3.1 pro

2- no comparison with any other model

Thanks, I will consider to add such granularities.