It goes beyond just running tests. From what I’ve tested on my website, it can actually detect and flag missing acceptance criteria that weren’t even specified, which is really useful. It also tests full scenarios and explores many different paths that a QA might sometimes overlook or simply not communicate. At least with Thunders, we become aware of those cases and can make a conscious decision to ignore them if they’re not relevant, rather than not knowing about them at all. Overall, it feels like a great AI assistant for making QA more thorough without adding extra manual effort.

It can save teams time and help teams increase end-to-end coverage improve release confidence

We use Thunders at Agorapulse (social media management platform, 40+ engineers) as the backbone of our release validation. What sets it apart is who uses it: our product managers, not QA engineers. They write automated test suites in plain natural language, replay them at every release, and own regression testing for their scope. This only became possible because the tool genuinely lowers the barrier: conditional steps, shared test cases with variables, personas, environments. The learning curve for a non-technical PM is measured in hours, not weeks. Beyond the accessibility, Thunders being AI-native changes the economics of test maintenance. Tests are executed by an agent that understands intent rather than relying on brittle selectors or XPath, so minor UI changes that would break a traditional Playwright suite simply don't. Our tests describe what a user wants to accomplish, and the agent figures out how. This drastically reduces the maintenance burden that usually kills E2E automation initiatives, and it means the product improves as underlying models improve, without us rewriting anything. The team ships fast and listens. We have run workshops with them on CI integration and run organization, and their responsiveness has been consistently good. Finally, the ROI conversation is straightforward. We found ourselves without dedicated QA headcount and no budget to rebuild that capacity. Rather than treating this as a coverage gap to live with, Thunders allowed us to rethink our process entirely: quality ownership moved to product managers, who now maintain the regression suites themselves. The tool's cost is marginal compared to the full-time positions it would have taken to solve the same problem the traditional way. In effect, a constraint became an opportunity to build a leaner, better model.