Journal
Writing
90 pieces · newest 8 September 2026
Evaluating Agent Quality -- Testing What You Cannot Unit Test
Build a repeatable evaluation pipeline for multi-agent correctness -- golden datasets, automated scoring, and CI/CD integration.
MCP Integration -- Connecting AI Agents to the Tool Ecosystem
Replace hand-coded tools with Model Context Protocol servers -- standardized tool discovery and execution for any agent framework.
Graph-Based Workflows -- Beyond Simple Orchestration
Move from LLM-driven routing to deterministic graph-based workflows -- sequential pipelines, parallel execution, conditional branching, and state management.
MAF v1 — Streaming and Multi-turn (Python + .NET)
Stream tokens as they arrive and reuse a session across turns so the LLM sees the full conversation. ~60 lines of code per language.
MAF v1 — Sessions (Python + .NET)
Serialize an AgentSession to JSON, persist it, reload in a fresh process, and have the agent pick up exactly where it left off.
MAF v1 — Setup your dev environment (Python + .NET)
Install uv, .NET 9, Docker, OpenAI keys, and a verify script so Chapter 1 starts with both Python and .NET environments ready.
MAF v1 — Your First Agent (Python + .NET)
Build the smallest useful Microsoft Agent Framework program: one LLM call, one response, and the same shape in Python and .NET.
MAF v1 — Adding Tools (Python + .NET)
Give an agent a callable function, let the LLM decide when to use it, and compare Python and .NET tool loops side by side.
What Is an AI Agent? (And When Should You Build One)
What AI agents actually are, how they differ from a plain LLM call, the patterns in production, and when an agent is the right call — and when it isn't.
Why I Switched from npm to pnpm (And Why You Should Too)
A practical breakdown of why pnpm beats npm for modern JS/TS projects — faster installs, strict dependency resolution, and monorepo support.
Building Dictum — a macOS Dictation App with Tauri 2 (Rust + React) & Azure OpenAI
Build Dictum, a macOS dictation app in Tauri 2 (Rust + React): hold-to-talk capture, Whisper transcription via Azure OpenAI, clipboard injection.
Azure App Registration: A Complete Guide from Zero to Working App
Everything about Azure App Registration — application types, authentication flows, client secrets vs certificates, redirect URIs, and how tokens work.
