Fun with AI Agents and the EU AI Act

2025 is shaping up to be the year when many organizations move beyond AI “proof of concepts” and start deploying AI chatbots and AI agents “for real”. Over the past months, I’ve had a number of interesting discussions with customers about how to approach this transition, and how to set up an AI infrastructure that is robust from both a technical and compliance perspective.

Unicorn story generation using the Semantic Kernel

Over the last couple of months, I have used the Semantic Kernel in different ways, usually as part of my exploration on how to use various LLMs together with the Dataverse MCP Server.

Automatic report generation using advanced MCP features

The Model Context Protocol specification has the goal of standardizing the way that Large Language Models (LLM) connect to your data sources and tools - like a USB-C for AI.

Foundry Local, the new OpenAI models and the Harmony response format

About a week ago (prior to the release of the highly anticipated GPT-5 model), OpenAI released its first open weights model since GPT-2, the gpt-oss-20b and gpt-oss-120b models.

I tried out gpt-oss-20b (the 20 billion parameter model) using LM Studio, and recorded a video showing how well the model handles tool-calling, using the Dataverse MCP Server.

The anatomy of FetchXML Builder with AI

Jonas Rapp has just released an update to FetchXML Builder that makes it possible to use AI to construct FetchXml queries - see the release notes and his post on LinkedIn.

As I have mentioned, I have had the pleasure of helping Jonas to implement this functionality, which has been fun in all kinds of ways.