LatestHypothesis
Describe the outcome, then check it: agentic AI and software testing
Notes from The Collective 2026: agentic AI as a new interface layer, what research says about trust in AI output, and why testers keep checking the result.
I am a QA consultant in the Netherlands, working on Pega, Tricentis Tosca and test automation. Here I write about what I see in practice: in projects, with AI, and in between.
Now Launched Field Notes: short notes from QA and delivery work, in English, Turkish and Dutch. What I’m doing now
Browse all postsFollow with a feed reader
LatestHypothesis
Notes from The Collective 2026: agentic AI as a new interface layer, what research says about trust in AI output, and why testers keep checking the result.
Longer pieces, rewritten until they hold.
Verified
All 249 tests passed after an AI agent wrote the code. A quality check still said no, and it was right.
Needs a re-run
Smaller thoughts, still being tested.
Working on test strategy for a Pega or Tosca project?