Building an AI System
From empty repo to production orchestration - every piece, in order.
A build-in-public series taking an AI system from an empty repo to a real, running Azure architecture - one piece at a time. Each piece starts simple and layers up to the full system, with the code and a one-command deploy (local or your own cloud) at the top so you can build alongside. The knowledge is all out there now; what's missing is a place to actually get your hands on it. This is that place.
- Part 1Jun 23, 2026 · 3 min readStart Here - Building an AI System
Why I'm building a full AI system in public, piece by piece - and how to follow along (and deploy it yourself).
- Part 2Jun 23, 2026 · 4 min readThe MCP Server on an Azure Function App
The foundation - standing up a Model Context Protocol server on a serverless Azure Function App.
- Part 3Jun 23, 2026 · 3 min readConnectors
Wiring the MCP server to the clients and data sources it talks to.
- Part 4Jun 23, 2026 · 3 min readData Flow
How data moves through the system, end to end.
- Part 5Jun 23, 2026 · 3 min readCustom Instructions
Shaping how the system behaves and stays on task.
- Part 6Jun 23, 2026 · 3 min readMulti-Client Wireup - ChatGPT, Claude Code, Grok, Copilot
One server, every client - connecting the same MCP to the tools you already use.
- Part 7Jun 23, 2026 · 3 min readWhere We Are Now
A checkpoint - the architecture as it stands so far.
- Part 8Jun 23, 2026 · 3 min readService-Side Infra - RAG, Vector, and a Local Service API
The brains - retrieval, vectors, and a local service API wired internal and external, in one resource group.
- Part 9Jun 23, 2026 · 3 min readExternal Tool Access
Letting the system reach out to the wider world, safely.
- Part 10Jun 23, 2026 · 3 min readThe Agent - an Azure AI Intelligence App
Tying it all together into an intelligent agent that helps manage Azure.
- Part 11Jun 23, 2026 · 3 min readBuild Your Own
Take the whole thing, install it, and build your own apps on top.