Benchmark Human QA Against an AI Tester on Three Apps

MerlinJourneys explores a website as every kind of user, maps the journeys and tests each flow end to end on desktop and mobile, with annotated screenshots and plain-language bug reports. We want an experienced QA engineer to put that to the test. Choose three open-source web apps and run them yourself. Test each one by hand, the way you would for a client, and separately run MerlinJourneys on the same apps with the access we give you. Deliverable: a comparison table of every issue found, who found it, its severity and which reports were wrong, plus a short write-up of what a careful human caught that the tool missed, and the reverse. Done means all three apps are covered and each disputed finding has steps to reproduce. Mandatory: exploratory testing, web application QA, bug reporting in Jira or Linear, browser DevTools. Nice to have: Playwright or Cypress, test strategy experience, ISTQB.