Category Helpers
EPPC26 Thursday keynote recap: Nirav Shah (Microsoft) introduces Agent 365 — the unified control plane for governing AI agents across Microsoft and third-party platforms. Covers the governance gap, shadow AI, KPMG case study (130K agents), local agent discovery, and new cost management features.
An EPPC26 Devlog — Automating Conference Recaps with Claude Code European Power Platform Conference, Copenhagen | June–July 2026 | Category: Claude Code Every conference blogger knows the real cost isn’t sitting in the session — it’s everything that happens after…. Continue Reading →
I have been building Power Apps Canvas Apps for years. The process has always had friction: design in the Studio, hit publish, wait, inspect the result, go back, adjust, repeat. It works, but it’s slow. So when I saw that… Continue Reading →
What happens when you don’t just build agents—but use agents to build agents? In my session “Agent Stories Part 1: Copilot Studio agent development with an agentic approach”, I walked through a very practical and hands-on example of how agent… Continue Reading →
As AI agents rapidly spread across organizations, one challenge becomes unavoidable: How do you keep them under control? I attended Microsoft partner architect seminar in Hilton Kalastajatorppa. I had one session about developing Copilot Studio agents with Claude Code and… Continue Reading →
I’ve been doing Copilot Studio agents and Power Automate flows with Claude Code. It was time to try to create a Power Apps with Claude Code. I wasn’t sure how to do that, I off course asked Claude and got… Continue Reading →
I created Power Automate flows with Claude for existing demo functionality it was time to test them. I used Claude to create me smoke test cases meaning happy path. I took the first flow into designer and looked what it… Continue Reading →
I started my virtual machine and entered Claude Code in CLI. This was not the same way as with Copilot Studio, that I first export empty agents into my virtual machine and then let Claude to work on them. I… Continue Reading →
At this point, I thought I was being smart. I already had a working Copilot Studio multi‑agent orchestration, and I wanted to see if GitHub Copilot with Power Platform Architect skills could “improve” it further. I let Copilot create a… Continue Reading →
After my test drives with agentic development and different LMMs I wanted to have agentic measurement. I took remote connection to my Ubuntu machine running Claude Code, OpenCode and GitHub Copilot and split the terminal. I ran those all three… Continue Reading →