How to create your own AI agent skill
Creating an AI agent skill means writing a Markdown file. Here’s how to structure it so the agent loads it at the right time.
[Read More]
.NET 10 Worker Service and Audio Pipeline
This post is part of the Voice Assistant on Raspberry Pi series.
Both Pis are configured. Time to write some code. The goal: validate the full audio pipeline on the pi-client, from button press to spoken response, without a real LLM. We hardcode a reply for now. The LLM comes in article #3.
The complete code for this article is available on GitHub.
[Read More]What is an AI agent skill?
Skills give your AI agent repeatable, portable behavior: without re-explaining your context at the start of every conversation.
[Read More]
Microsoft Agent Framework: First Agent, MCP, and Multi-Agent Workflows
Microsoft Agent Framework replaces Semantic Kernel and AutoGen. Here’s how to create a local agent with Ollama, connect an MCP server, and orchestrate two agents in sequence.
[Read More]
MCP in C#: Exposing Your Own Tools to Any AI Client
MCP standardises how AI clients call external tools. Here’s how to build a working MCP server in C#: with a complete weather example, ready to connect to Claude Desktop or VS Code Copilot.
[Read More]
Building AI Agents with Ollama and .NET
Learn how to create AI agents that think, plan, and act autonomously using Ollama and .NET. Explore the ReAct pattern, tool calling, and practical agent architectures.
[Read More]
Local RAG with Ollama, LiteLLM, and Qdrant
Wire up Ollama to LiteLLM and Qdrant for local RAG: ingestion, chunking, embeddings, retrieval, and basic evaluation.
[Read More]
Local AI Development with Ollama and .NET
Learn how to run large language models locally using Ollama and integrate them into your .NET applications for enhanced privacy, reduced costs, and offline AI capabilities.
[Read More]
Supabase and Table Relationships
For one of my .NET projects, I use Supabase to store my data. Supabase is an open-source alternative to Firebase. It is based on PostgreSQL and provides a REST API and websockets to interact with the database.
To connect my .NET project to Supabase, I use Supabase Sharp and you can also find the documentation on the official Supabase website.
The ease of use of the library is really interesting and it also allows me to use the Supabase website directly to manage my data without having to write code to do it in my own applications.
[Read More]