Tag copilot studio
AI agents often stay at the edges—chatbots, assistants, or isolated use cases. But the real value starts when agents are embedded inside core business processes. I attended Microsoft partner architect seminar in Hilton Kalastajatorppa. I had one session about developing… Continue Reading →
AI conversations often focus on complexity—multi-agent systems, advanced architectures, and large-scale transformations. But what if the real value comes from something much simpler? I attended Microsoft partner architect seminar in Hilton Kalastajatorppa. I had one session about developing Copilot Studio… 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 →
At some point, every Copilot Studio conversation hits a limit. Simple chat-based agents are easy to build.But real business problems rarely stay simple. I attended Microsoft partner architect seminar in Hilton Kalastajatorppa. I had one session about developing Copilot Studio… 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 →
AI in business applications often sounds abstract until you see where it removes real work. I attended Microsoft partner architect seminar in Hilton Kalastajatorppa. I had one session about developing Copilot Studio agents with Claude Code and then I participated… 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 →
After trying out Claude Code and OpenCode it is time you test GitHub Copilot CLI. I was a bit skeptical, since this is already old stuff and I had couple licenses to this. But GitHub Copilot suprised me very well… Continue Reading →
Earlier I created Copilot Studio agent with Claude Code, now it is time to test OpenCode. Intallation was quite simple, just one command and it was there like Pasi Huuhka promised. I was thinking this would take one hour struggle… Continue Reading →