Action is the most beautiful form of speech

Tag testing

Scheduling a Copilot Studio agent test: the evaluation call returns a run, not a result

Agent instructions change constantly. Someone widens a trigger phrase, someone adds a knowledge source, someone rewrites a topic to remove a stale link. Each change is small and defensible on its own, and none of them tell you what happened… Continue Reading →

Defensible beats impressive: designing a governed Copilot Studio agent

A confident wrong answer sounds helpful. It is the worst possible outcome, because nobody thinks to check it. “I don’t know” sounds worse and is better: it can be defended, and it tells the user what to do next. I… Continue Reading →

Test-Driven Agent Development

I have been building quite a different kind of Copilot Studio agents, but this latest project was the most challenging one. The knowledge source list was very narrow, and the agent was not allowed to hallucinate or to say anything… Continue Reading →

Play it (w)right — Automating End‑to‑End Tests in the Power Platform

At CollabDays Bremen 2026, I attended the session “Play it (w)right: automate your end-to-end tests in the Power Platform.” held by Arjan Rijsdijk (slides). This was one of the most practical, demo-rich experiences of the entire event, and it completely… Continue Reading →

AI driven Power Automate development

There is possibility create Power Automate flows with Copilot and I think that does not even requires any specific Copilot license, just the normal license for generating Power Automate flows. As the other tools Copilot marketing sounds too good to… Continue Reading →

© 2026 Karl-Johan Spiik, Microsoft MVP — Powered by WordPress

Theme by Anders NorenUp ↑