
Founded by Shivam Agrawal & Aaron Yu
Shipping a great mobile app is hard. Even top teams struggle with flaky end-to-end tests, missed edge cases, and regressions that slip past CI.
Script-based automation tools like Playwright, Selenium, Appium or Espresso break often. Visual diff tools miss functional bugs. And in-house human QA teams can’t scale with today’s release cycles.
CTOs, VPs, Directors of Eng, and QA leads at fast-growing companies are asking:
Why does their test suite say green when their users say broken?
The team has been mobile engineers at Google who shipped products like Android XR, Quick Share, Stadia, and foldable phones. They have seen firsthand how slow, flaky QA can derail a great product. They built QualGent so teams can catch real bugs faster, ship with confidence, and stop wasting time maintaining fragile tests.
They are grateful to be part of the YC community and excited to bring modern AI to a painful, expensive problem that slows down almost every mobile team they have met.
QualGent uses computer-use LLM agents and vision models to mimic a real human tester:
No more rigid scripting. No more emulator-only limits. No more test maintenance hell.
Theur AI agent self-heals, handles dynamic pop-up content, navigates unexpected UI changes, and catches bugs like a pro.
Their vision is to close the loop on software creation. As AI enables engineers to code 100x faster, QualGent eliminates the next bottleneck—software verification—unlocking truly scalable, end-to-end product-driven software development.