Writing.
Two series, told in order - a build-log of an AI system going up piece by piece, and a reading room of the ideas behind it.
Start 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).
The MCP Server on an Azure Function App
The foundation - standing up a Model Context Protocol server on a serverless Azure Function App.
Connectors
Wiring the MCP server to the clients and data sources it talks to.
Data Flow
How data moves through the system, end to end.
Custom Instructions
Shaping how the system behaves and stays on task.
Multi-Client Wireup - ChatGPT, Claude Code, Grok, Copilot
One server, every client - connecting the same MCP to the tools you already use.
Where We Are Now
A checkpoint - the architecture as it stands so far.
Service-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.
External Tool Access
Letting the system reach out to the wider world, safely.
The Agent - an Azure AI Intelligence App
Tying it all together into an intelligent agent that helps manage Azure.
Build Your Own
Take the whole thing, install it, and build your own apps on top.
What an AI Agent Actually Is
Everyone says 'agent' like it's magic. It isn't; it's a loop. Here's the whole idea in plain English.
Tokens and the Context Window
What the model actually sees; and why it seems to forget things mid-conversation.
Embeddings: How a Computer Gets Meaning
How words and ideas become numbers a machine can actually compare.
RAG in Plain English
Retrieve-then-generate; what it is, and when it beats fine-tuning.
Tool Calling: How an LLM Actually Does Things
How a text-only model reaches out and acts on the real world.
MCP, Explained
One plug for every tool; why everyone is suddenly shipping an MCP server.
What an Eval Is
How you measure an AI system before shipping it, so 'is it better?' stops being a vibe.
The True Cost of One LLM Call
Tokens, latency, and dollars; the real math behind a single call.
System diagrams and design concepts
The visual companion to the writing - AI orchestration, cloud, and agent diagrams I keep coming back to.