Topics
Ideas that run across several posts: what the posts say, and where they changed their minds
A category is a shelf of posts. A topic is a short summary of one idea, with every claim quoted from the post it came from. The posts are the authority.
AI agents
10 postsMy posts explore the capabilities of AI agents in executing complex tasks, from building games and hardware integrations to automating legal documentation.
- DeepSeek Harness (Part 3)
- ATtiny85 (Part 1)
- Spec-Driven AI Tools (Part 3)
- Spec-Driven AI Tools (Part 4)
- Spec-Driven AI Tools (Part 1)
- Spec-Driven AI Tools (Part 2)
- DeepSeek Harness (Part 2)
- Claude Code (Part 15)
- DeepSeek Harness (Part 1)
- Claude Code (Part 14)
Azure AI Foundry
10 postsI explore the capabilities of Azure AI Foundry for building and deploying intelligent agents.
- Azure Foundry Agent (Part 7)
- Azure Foundry Agent (Part 6)
- Where to start in Microsoft Foundry
- Azure Foundry Agent (Part 5)
- Azure Foundry Agent (Part 3)
- Azure Foundry Agent (Part 4)
- Azure Foundry Agent (Part 1)
- Azure Foundry Agent (Part 2)
- Azure Search (Part 2)
- Power Automate
Business Central development
10 postsI cover a wide range of Business Central development topics, from core integration techniques to advanced AI and external service connections.
- Business Central (Part 8)
- Business Central Azure Functions (Part 2)
- Business Central Azure Functions (Part 1)
- Business Central Azure Logic App
- Business Central (Part 7)
- Copilot Studio Agent Tools
- Model Context Protocol (Part 2)
- Customer Copilot Studio
- Business Central (Part 5)
- Power Pages (Part 2)
Claude Code
10 postsI use Claude Code as a powerful tool to automate complex tasks ranging from hardware programming and 3D design to software development and data integration.
- Claude Code (Part 17)
- SingSaber
- 3D Printing (Part 3)
- Claude Code (Part 16)
- ATtiny85 (Part 1)
- Spec-Driven AI Tools (Part 3)
- Spec-Driven AI Tools (Part 4)
- Spec-Driven AI Tools (Part 1)
- Spec-Driven AI Tools (Part 2)
- Model Context Protocol (Part 4)
Copilot Studio
8 postsI explore how Copilot Studio serves as a powerful engine for building custom agents and integrating them with platforms like Business Central and model-driven apps.
- Adding a Custom Topic to the Copilot in a Model-Driven App
- Copilot Studio Agent Tools
- Customer Copilot Studio
- Blog Copilot Studio
- Custom Copilot Studio
- Configure Copilot single sign-on for Web
- Copilot Studio
- Create action based on a flow
Docker
7 postsI use Docker to create, manage, and deliver applications across various hardware platforms and environments.
- Scikit-Learn (Part 19)
- Agentic AI for Professionals (Part 3)
- Agentic AI for Professionals (Part 2)
- Prompt Flow (Part 2)
- Amazon Elastic Container Service
- Microsoft SQL Server (Part 1)
- Docker
Dynamics 365 and CRM
8 postsI explore the evolution, configuration, and practical application of Microsoft Dynamics 365 and its underlying Dataverse platform.
- Dynamics 365 Sales (Part 4)
- Customising a HubSpot Quote Template with a Child Theme
- Microsoft Dynamics 365 App for Outlook
- Dynamics 365 Sales (Part 1)
- Dynamics 365 Sales (Part 2)
- Dynamics 365 Sales (Part 3)
- A Short History of Microsoft Dynamics and Microsoft Dataverse
- Dynamics Trial Signup
Machine learning in Python
10 postsI explore the vast landscape of machine learning in Python, covering everything from deep neural networks and natural language processing to reinforcement learning and production deployment.
- Scikit-Learn (Part 11)
- Scikit-Learn (Part 12)
- Scikit-Learn (Part 13)
- Scikit-Learn (Part 14)
- Scikit-Learn (Part 15)
- Scikit-Learn (Part 16)
- Scikit-Learn (Part 17)
- Scikit-Learn (Part 18)
- Scikit-Learn (Part 19)
- Scikit-Learn (Part 20)
MLX on Apple silicon
7 postsI explore how the MLX framework optimizes the performance of large language models on Apple Silicon.
- MiniGPT (Part 4)
- MiniGPT (Part 5)
- MiniGPT (Part 6)
- MiniGPT (Part 7)
- Distillation (Part 2)
- Distillation (Part 1)
- MLX 1
Model Context Protocol
8 postsI explore the Model Context Protocol as a standard way to provide AI agents with tools and real-time data.
- Azure Foundry Agent (Part 5)
- Azure Foundry Agent (Part 3)
- Model Context Protocol (Part 4)
- Model Context Protocol (Part 3)
- Agentic AI for Professionals (Part 3)
- Claude Code (Part 7)
- Model Context Protocol (Part 2)
- Model Context Protocol (Part 1)
Power Apps and Dataverse
10 postsI explore the diverse capabilities of Dataverse as a robust backend for Power Apps, ranging from core configuration and integration to advanced automation.
- Coding Agents That Never Leave?
- Claude Code (Part 16)
- Model Driven Apps Timeline
- Claude Code (Part 13)
- Adding a Custom Topic to the Copilot in a Model-Driven App
- Customizing Status Reasons in Power Platform
- SharePoint (Part 2)
- SharePoint (Part 1)
- Power Apps (Part 1)
- Business Central (Part 4)
Power Automate and integration
10 postsI explore how Power Automate serves as a versatile integration engine to connect diverse systems like SharePoint, Business Central, and Azure AI Foundry.
- SharePoint (Part 2)
- SharePoint (Part 1)
- Power Automate
- Business Central (Part 8)
- Business Central Azure Functions (Part 1)
- Business Central Azure Logic App
- Business Central (Part 4)
- Microsoft Power Automate Reports
- Cloud Flow
- Create action based on a flow
Raspberry Pi
10 postsI use the Raspberry Pi for a wide range of projects including retro gaming, voice-controlled assistants, and IoT management.
- Picade Console
- Voice Kit (Part 4)
- Voice Kit (Part 3)
- Voice Kit (Part 2)
- Voice Kit (Part 1)
- Gingerbread House
- Raspberry Pi SH1106
- Raspberry Pi Imager
- 3D Printing (Part 2)
- Internet of Things (Part 2)
Retrieval-augmented generation
9 postsRetrieval-augmented generation (RAG) improves the accuracy and specificity of large language model responses by providing relevant context from a knowledge base at runtime.
- Azure Foundry Agent (Part 6)
- Azure Foundry Agent (Part 5)
- Model Context Protocol (Part 3)
- Agentic AI for Professionals (Part 3)
- Agentic AI for Professionals (Part 1)
- Agentic AI for Professionals (Part 2)
- Azure Search (Part 2)
- LangChain (RAG)
- Context Injection
Rules-first design
2 postsUsing AI to build and maintain a rules base from the law, then running the rules, not the AI, when someone asks: what the Minnesota DWI advisor posts show, and where the approach is weaker than the first post claimed
Read the topic →Running models locally with Ollama
10 postsI have explored using Ollama to run models locally for various applications, including game development and automated agent workflows.
- Local Agent (Part 2)
- DeepSeek Harness (Part 3)
- DeepSeek Harness (Part 2)
- Agent Orchestration (Part 1)
- Agent Orchestration (Part 3)
- Model Context Protocol (Part 3)
- Agentic AI for Professionals (Part 2)
- Local Agent (Part 1)
- LLM Wiki
- Claude Code (Part 11)
SharePoint, Microsoft Graph and sign-in
10 postsI explore various methods for managing authentication and data integration across SharePoint and other Microsoft services.
- Coding Agents That Never Leave?
- SharePoint (Part 2)
- SharePoint (Part 1)
- ShareGate (Part 2)
- ShareGate (Part 1)
- SharePoint Syntex
- Configure Copilot single sign-on for Web
- Codespaces and Authentication
- Business Central Microsoft Graph
- Angular Firebase
Spring Boot
7 postsI explore the versatility of Spring Boot by building everything from REST APIs and GraphQL endpoints to full-stack web applications.
- Java Spring Boot (Part 7)
- Java Spring Boot (Part 6)
- Java Spring Boot (Part 5)
- Java Spring Boot (Part 4)
- Java Spring Boot (Part 3)
- Java Spring Boot (Part 2)
- Java Spring Boot (Part 1)