MCP

By the end of this post you will know what every iteration of every production agent must produce BEFORE it decides anything: four small artifacts that catch the failures sharper prompts cannot prevent. You will know why “tell the model to be careful” never worked as a defense, and why the only durable fix is structural. And you will know what the discipline looks like in code, because we have been running it at MACONA for months and the receipts are public. ...

By the end of this post you will know which of the five infrastructure control points your agent stack is shipping without, and you will have a concrete pattern for paying down the observability piece of that debt: a public, consumer-readable audit-trail receipt that satisfies both your security team and your finance team with the same document. The receipt was already in production when the broader practitioner conversation started naming the gap. ...

Update, 2026-05-19: A2A agent-card now live at mcp.adotob.com/.well-known/agent.json, published 24 hours after Nate B Jones’s IO-2026 video named the agent-card primitive as the second of the four core agent-protocol layers. Three of the four layers of the open-protocol stack are now live in the storefront: MCP for tool access, A2A for agent discovery, and AG-UI manifested as the public receipt page. AP2/X402 is reserved for the MVP-2 paid Stripe flow. By the end of this post you’ll have two public URLs you can forward to your security team AND your finance team — and both audits get satisfied by the same document. That document is an agent receipt. The two URLs are real receipts produced by the same MCP endpoint, one driven by Anthropic-hosted Claude Desktop and the other driven by Qwen3.6 27B running fully offline on my MacBook. The point of this post is why that one-artifact-two-ledgers property matters more than the technology that produces it. ...

TL;DR I went heads down for about three months — no LinkedIn, no YouTube, barely any Twitter. In that time I shipped two iOS apps to the App Store, built an autonomous AI assistant that runs a nonprofit’s entire digital presence 24/7, and developed a workflow where AI agents scale my output 3-5x. This post is the full story: the career pattern that taught me to recognize seismic shifts, what I actually built, and why I’m back. ...

🚀 Purpose In today’s fast-paced technology landscape, I found myself immersed in my journey at TechCon 365 Dallas 2025. What used to take me days to achieve now unfolds in merely two hours. This blog explores how technology has reshaped my workflow, allowing more efficient operations while emphasizing the importance of manual oversight along the way. During my preparation for the conference, I utilized multiple technologies including Graph, MCP, and Agents to create a streamlined process. While automation plays a significant role, I learned that having manual guardrails in place is essential. This realization stems from my familiarity with coding and the underlying tech, which often serves as a critical asset in navigating unexpected challenges. ...

🛒 Introduction 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. The idea was simple: Could a website behave like a full sales team — not just a storefront, but a conversation-led experience where agents guide, pitch, and close? So I prototyped it. It works. You can test it live right now at fabiangwilliams.com 🧠 What Is Agent-First Commerce? Traditional e-commerce relies on catalogs, carts, and checkouts. Agent-First Commerce introduces a conversational pipeline where AI agents assume roles: ...

🧠 Debugging GenAI with NLWeb and OpenTelemetry: A Real-Time Visibility Win “If you can’t see it, you can’t debug it.” That’s been the challenge with GenAI and Copilot-style plugins — until now. 🎯 Goal I wanted to trace and troubleshoot my Copilot agent plugin activity using OpenTelemetry. The stretch goal? Pipe that into a natural-language search experience using NLWeb, so I could ask questions like: “What plugins were used?” “What calls failed?” “How long did token generation take?” ✅ As of today — we did it. Here’s how. ...

🚀 Introduction This guide captures a modern, evaluation-first approach to building AI-powered projects using tools like GitHub Copilot, Claude, ChatGPT, and local LLMs like LLaMA and DeepSeek. We’ll use AsyncPR — a real-world mobile app project I built and shipped — as the public example. Check out a YouTube short video I did here on the App https://go.fabswill.com/asyncpr-shortintro and feel free to test it out! This guide reflects how I work today: VS Code as my IDE, Copilot for code assist, and running private models on my MacBook when needed for security or speed. ...