Case study, September to October 2026
175 bugs, two kinds of tester
What our automated test agents found, what our human testers found, and why fast-moving teams need both. Two client projects, every bug sorted by who found it, by kind and by severity.
Get the two-page report
Enter your details and the download opens right here.
We use your details to follow up once about this report. No newsletter, no sharing with anyone else.
The pattern in one line
The agents are strongest where the problem lives in code, APIs and markup. People are strongest where the problem only shows up when a real person uses the product, in a real place, in their own language.
| Found by | Critical | High | Medium | Low | Total |
|---|---|---|---|---|---|
| Human testers | 2 | 28 | 47 | 39 | 116 |
| Test agents | 4 | 7 | 33 | 15 | 59 |
Both sides found critical bugs. Drop either and real, expensive problems ship. The report has the full breakdown by kind of bug and the cases only one side caught.
Try it on your product
Pick the one flow your customers use most. We run agents and a tester on it for a day, complimentary, and show you what each side finds.
How we counted: all 175 bugs filed on two client projects between 27 September and 29 October 2026, sorted by who found them and by kind. Severity is as filed. Client names withheld.