Ollama Integration and Home Context
Posted on May 15, 2026
| Reading time: 7 min
| 1286 words
| Gabriel Mongeon
• Other languages: fr
This post is part of the Voice Assistant on Raspberry Pi series.
Article #2 ended with a hardcoded response, which was enough to confirm the audio pipeline works. Now we swap that line for a real HTTP call to Ollama on the pi-cerveau, and add a system prompt to give the assistant a personality and some knowledge about your home.
The complete code for this article is available on GitHub.
[Read More]Setting Up Both Raspberry Pis
Posted on May 15, 2026
| Reading time: 5 min
| 953 words
| Gabriel Mongeon
• Other languages: fr
This post is part of the Voice Assistant on Raspberry Pi series.
Two Raspberry Pi 4s, a few hours of setup, and at the end you have a voice assistant running entirely on your local network. Before writing a single line of .NET code, here’s the setup for both Pis.
[Read More]How to create your own AI agent skill
Posted on May 8, 2026
| Reading time: 5 min
| 948 words
| Gabriel Mongeon
• Other languages: fr
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
Posted on May 1, 2026
| Reading time: 7 min
| 1331 words
| Gabriel Mongeon
• Other languages: fr
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?
Posted on May 1, 2026
| Reading time: 3 min
| 474 words
| Gabriel Mongeon
• Other languages: fr
Skills give your AI agent repeatable, portable behavior: without re-explaining your context at the start of every conversation.
[Read More]Create a Blazor App with ML.NET
Posted on April 26, 2026
Last modified on March 28, 2026
| Reading time: 6 min
| 1152 words
| Gabriel Mongeon
• Other languages: fr
Learn how to integrate ML.NET into a Blazor Server app to build a sentiment analysis tool using binary classification.
[Read More]PR preview environments
Posted on April 11, 2026
| Reading time: 4 min
| 697 words
| Gabriel Mongeon
• Other languages: fr
Sixth and final article in the series. We explore SWA’s preview environments: each pull request generates a complete environment with its own URL.
[Read More]Local development with the swa CLI
Posted on April 9, 2026
| Reading time: 5 min
| 896 words
| Gabriel Mongeon
• Other languages: fr
Fifth article in the series. We set up the swa CLI for local development with the proxy, the Functions API and authentication emulation.
[Read More]SWA's built-in authentication
Posted on April 7, 2026
| Reading time: 5 min
| 964 words
| Gabriel Mongeon
• Other languages: fr
Fourth article in the series. We explore SWA’s built-in authentication: the built-in providers, the /.auth/ endpoint, and how to get the user in Blazor and in the API.
[Read More]Adding an Azure Functions API
Posted on April 5, 2026
| Reading time: 5 min
| 1063 words
| Gabriel Mongeon
• Other languages: fr
Third article in the series. We add an Azure Functions API to our Blazor WASM project, call it from the client without fighting CORS, and deploy the whole thing.
[Read More]