Thunders Reviews & Product Details

What I like most is the simplicity of the approach. You can describe what you want to test in plain language and let the AI agent handle the browser, instead of spending time maintaining fragile automation scripts. I’m not a daily production user, but from what I’ve seen, this could be especially useful for manual QA teams that want to automate more without adding a lot of technical overhead. Review collected by and hosted on G2.com.

Nothing major from what I’ve seen so far. I think having more examples, templates and integrations would make the onboarding even easier, especially for teams that are new to AI-powered test automation. Review collected by and hosted on G2.com.

We use Thunders at Uptale and I’ve been really impressed by the product.

What stands out is the AI-native approach to QA automation. Plain-language test authoring combined with an agent that actually drives the browser makes testing much more approachable than maintaining traditional scripted test suites.

I especially like that it makes test automation accessible to our Product team, not just developers, so the people defining features and user flows can contribute directly to end-to-end testing. It also addresses a very concrete pain point for us: reducing the amount of manual regression testing we have to do before releasing to production.

The direction around reducing brittle test maintenance and making broader end-to-end coverage easier to achieve is very compelling. Review collected by and hosted on G2.com.

There’s quite a lot the product can do, so it takes a bit of time initially to understand how to get the most out of it and how to best integrate it into our existing QA and product workflows.

More guidance, templates and best-practice examples for different testing scenarios would make that initial adoption even easier. Review collected by and hosted on G2.com.

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. Review collected by and hosted on G2.com.

The product is getting more and more maturity let’s see for the moment nothing much to say Review collected by and hosted on G2.com.

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. Review collected by and hosted on G2.com.

More advanced documentation would be helpful. Since LLMs aren’t deterministic, having more guidance and examples would make it easier to get high-quality results faster Review collected by and hosted on G2.com.

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. Review collected by and hosted on G2.com.

Natural language tests require discipline in how instructions are written: ambiguous steps can lead the agent to select the wrong element, so we invested in internal writing guidelines. Not a flaw of the tool per se, but a real onboarding cost to anticipate. Review collected by and hosted on G2.com.

The plain-language authoring is what stands out to me. You describe the check in normal English and an agent drives the browser, so a UI change doesn't take the whole suite down the way a Selenium or Playwright script does. For teams without dedicated automation engineers, that's the difference between having regression coverage and skipping it. Review collected by and hosted on G2.com.

The documentation could go deeper. There's a lot of capability under the surface, and getting to the more advanced features takes more exploring than it should, more worked examples and templates would shorten that ramp. Review collected by and hosted on G2.com.

The interface is genuinely good, and the Thunders copilot is what makes the whole thing click. It gives you confidence while you are building a test, and it visibly raises the quality of what you end up writing rather than just getting you to something that runs.

The product team ran the evaluation, but the effect went well beyond us: it raised the maturity of the whole team, product and engineering alike, on testing as a subject. Because writing a test no longer requires being technical, it became a shared conversation instead of a specialist one.

Concretely, it let us redraw roles and responsibilities. Product now owns very precise acceptance tests and edge case QA, where our knowledge of the expected behaviour is the differentiator. Engineering keeps the rest. That split was not realistic before, and it is the change I value most.

The practical result is that we write end to end non regression tests much earlier in the cycle. Previously that was a project in itself, so it kept being postponed. We now go into releases with a high level of confidence that existing behaviour has not broken. Review collected by and hosted on G2.com.

One narrow caveat, and it is not the main use case. If what you want specifically is to speed up the very first steps of manual QA, temper your expectations: there is still real setup work involved and the AI does not handle everything on its own yet. That is a sub use case, not what the product is mainly built for or where we get our value from. The team moves fast and is actively working on it, so I expect it to become a must have in the next iterations. Review collected by and hosted on G2.com.

What stood out most during our trial was generating tests in natural language. As a growing enterprise B2B SaaS startup, we have multiple products, languages, and customer-specific requirements, but no dedicated automation engineers yet. Making automation accessible to our existing QA team is particularly valuable. From the trial, demo, and conversations with the team, I see strong potential to expand our test coverage and reduce the manual regression testing bottleneck before releases. Review collected by and hosted on G2.com.

Based on our trial, I’d like richer reporting and tracking to make it easier to follow test results over time, understand coverage across products and customer-specific scenarios, and identify where our QA team should focus next. Review collected by and hosted on G2.com.

The no-code approach is what sold us from the start. Being able to describe test scenarios in plain language meant we could involve anyone, including young interns with no automation background. It turned into a practical way to onboard them into quality testing for our websites, and they picked it up quickly.

Over the past year, I’ve watched the product evolve at an impressive pace. New features kept arriving regularly, and it was clear the team was actively listening to feedback. Their support has also been outstanding. We started using Thunders fairly early on, and whenever we ran into an issue, their team responded quickly and was genuinely helpful. That kind of responsiveness makes a huge difference when you’re betting on a young product. Review collected by and hosted on G2.com.

The tool is still maturing, and it shows in spots, documentation could go deeper on advanced use cases, and on very complex flows the AI sometimes needs a few iterations to get the scenario right. Minor growing pains overall. Review collected by and hosted on G2.com.

Thunders makes test automation far more accessible. Being able to describe what I want to test in natural language and then let the AI take care of creating and running the tests feels like a real game changer. I also appreciate that the product is grounded in real testing expertise, instead of just layering AI on top of an existing tool. On top of that, the team is responsive and pragmatic, and they clearly understand the day-to-day challenges product and engineering teams face. Review collected by and hosted on G2.com.

There are a few areas that could be improved, particularly when it comes to advanced use cases and certain edge cases. Review collected by and hosted on G2.com.