If you’ve ever wanted a single repo that lets you flip a switch between a locally‑hosted LLM, a hosted OpenAI model, and a Python‑based evaluation suite—while keeping every call visible in a unified observability stack—this is it.
Fabian G. Williams
Principal Product Manager, Microsoft Subscribe to my YouTube.
Agent-First Commerce: I Built a Website That Sells Like a Sales Team
Over a weekend, I built and tested a working Agent-First e-commerce demo with Claude Code, MCP, and conversational checkout. Here's what I learned.
Not selling anything here — just sharing what I built over a weekend using Claude Code, the Model Context Protocol (MCP), and Agent-to-Agent (A2A) orchestration.
Debugging GenAI with NLWeb and OpenTelemetry: A Real-Time Visibility Win
We used NLWeb and OpenTelemetry to trace, debug, and query Copilot agent plugins — all in real-time.
Recent Posts
Agent + Local Model + Evals — One‑Pager
Agent-First Commerce: I Built a Website That Sells Like a Sales Team
Debugging GenAI with NLWeb and OpenTelemetry: A Real-Time Visibility Win
Vibe Coding with AI – Best Practices for Every Project
Start with Why: The How, the Why, and the What Behind My Reading Habit
Categories
About
Fabian G. Williams aka Fabs Site