From what I’ve seen so far, an AI-native approach seems to be the most promising direction for QA automation.

the AI-native approach feels like the right direction for QA automation. Instead of recording brittle Selenium/Playwright/Cypress scripts, you describe tests in plain language and an AI agent drives the browser itself. That design should make suites far less prone to breaking every time the UI changes — which is the classic pain point with traditional test automation. It is especially useful for manual QA teams or product teams shipping fast without a big bench of automation engineers. It can help reduce test maintenance and increase end-to-end coverage without piling more work onto the team, which in turn can support faster regression testing and more release confidence. Overall, based on what I’ve tested, Thunders has real potential to replace the flaky, maintenance-heavy automation setups a lot of teams are stuck with today.

Thunders is the solution that reflects the best how testing should looks like in the agentic era. I had the chance to witness the progress of this product and the evolution was phenomenal