Category: #AI

This is my 4th newsletter on AI and .NET topics 🚀 focussing on AI use cases, software architecture, and production-grade patterns. If you’re working hands-on with .NET, AI, or relevant enterprise architectures, feel free to connect 👋, follow 🔔, or jump into the discussion. AI Toolkit for VS Code: Microsoft released AI Toolkit 0.30.0, which materially advances VS Code’s support for agent development by improving discoverability, structured evaluation, real debugging, and deeper integration with Microsoft

This is my 3rd newsletter on AI and .NET topics 🚀 focussing on AI use cases, software architecture, and production-grade patterns. If you’re working hands-on with .NET, AI, or relevant enterprise architectures, feel free to connect 👋, follow 🔔, or jump into the discussion. • GitHub Copilot SDK enters technical preview, expanding agent architecture options: The GitHub Copilot SDK was released in technical preview during the past week, enabling developers to embed the same agentic

This is my 2nd newsletter on AI and .NET topics 🚀 focussing on AI use cases, software architecture, and production-grade patterns. If you’re working hands-on with .NET, AI, or relevant enterprise architectures, feel free to connect 👋, follow 🔔, or jump into the discussion. • Core AI foundations for .NET: Recent .NET Foundation guidance on the Microsoft.Extensions.AI libraries underscores a deliberate push toward stable, composable abstractions for generative AI integration. Interfaces such as IChatClient and

Welcome to 2026 🚀 With the new year, I am starting a regular news update on AI topics in the  .NET world, focussing on AI use cases, software architecture, and production-grade patterns. If you’re working hands-on with .NET, AI, or relevant enterprise architectures, feel free to connect 👋, follow 🔔, or jump into the discussion. • .NET 10 positions agent-based AI as a first-class architectural pattern: With .NET 10, Microsoft consolidates agent orchestration patterns (Semantic

Quantum programming is becoming more accessible thanks to Azure Quantum Copilot. Basically it works analogue to the known Copilot technologies, only for Q#. So let’s see how it works! 1. Visit the Azure Quantum web portal at https://quantum.microsoft.com/en-us/tools/quantum-coding. 2. Write your prompt, e. g. ‘Write code to create two qubits, entangle them, and measure them.”3. Execute the generated code either in your Visual Studio Code environment with QDK or directly within the Azure Quantum web

After giving you a snipplet on how to create a Qubit in superposition in Q#, let’s have look how to run this program via your Visual Studio Code instance using the Microsofts Quantum Development Kit (QDK). To run the snipplet on a simulator or even on real quantum hardware Microsoft Azure Quantum service is the place, where you have to start. The service offers to test several Quantum computation approaches. Here’s a quick overview of

And now for something different: with all the hype about Quantum computing, I felt like having a sharp look in Q# to find out, where we are at the moment. Quantum computing isn’t just about speed, its also a paradigm shift. Unlike classical bits (0 or 1), qubits can exist in a superposition of both. This enables parallelism at a fundamental level compared to our well-known digital computer architectures. Just image neuromorphic architectures on Quantum

OpenAI ChatGPT can be a customized API for your application by generating machine-readable output for your prompt. The model behind can be either the current GPT-4 model or a fine-tuned model with your own business data provided via an extended context or functions. This article shows you how to generate machine-readable JSON from OpenAI ChatGPT using OkGoDoIt OpenAI-API using C#/.NET. Generating machine-readable output can be a challenge as ChatGPTs prompt closure is non-deterministic. I write

My last post on OpenAI ChatGPT showed how to use ChatGPT in a .NET application using the Azure.AI.OpenAI library. This package went meanwhile to beta version 1.11.0-beta.1 and thus the usage of the ChatCompletionOptions has changed a little bit, you guess you will note it in your applications and tests. For todays example I use OkGoDoIt OpenAI-API library, as I want to show you how to connect to OpenAI without using Azure services and also

So, let’s get to OpenAI ChatGPT, as it resounds throughout the land, how big and good it is 😉 Also there might be some open-source LLMs with equal capabilities, let’s have a specific look at that LLM as it’s currently the most relevant for business applications. For .NET applications it’s relevant, that Microsoft offers OpenAI ChatGPT through its Azure subscription. Most companies will use the Azure API wrappers for OpenAI ChatGPT usage, simply because most