AI Engineering
How I Built an Autonomous QA System That Tests My App While I Sleep
How to build an autonomous AI QA system with Claude Code, Playwright, and GitHub Actions — nightly tests while you sleep. Full architecture, real cost breakdown.
AI Engineering
MCP Servers
300+ MCP Combo Patterns That Make AI Agents Actually Useful
Most developers install MCP servers and use them one at a time. The real power is in the combos. Here are 85 patterns I use daily to run a production SaaS from my terminal.
Career
What I'd Tell Every PM Starting Their AI Journey Today
What I'd Tell Every PM Starting Their AI Journey Today | AI PM Portfolio What I'd Tell Every PM Starting Their AI Journey Today March 30, 2026 · 18 min read · Career Advice / Closing Post After 7 years of building AI products -- from rule engines in logistics
Career
The 7-Year Arc: From Rule Engines to Autonomous Agents
The 7-Year Arc: From Rule Engines to Autonomous Agents | AI PM Portfolio The 7-Year Arc: From Rule Engines to Autonomous Agents March 10, 2026 · 24 min read · Career Retrospective / Definitive Guide Seven years ago, I built rule engines for logistics automation. Today, I build autonomous AI agents that process 128,
Product Strategy
Why 'Prevention Doesn't Sell' Is the Biggest AI Product Challenge
Why "Prevention Doesn't Sell" Is the Biggest AI Product Challenge | AI PM Portfolio Why "Prevention Doesn't Sell" Is the Biggest AI Product Challenge February 20, 2026 · 16 min read · Behavioral Economics / Product Strategy The hardest lesson from building AI products for 1,
LLMs
Gemini vs Claude vs GPT in Production: A PM's Honest Comparison
An honest head-to-head of Gemini, Claude, and GPT in production — accuracy, cost, latency, and when to pick each. Based on 128K docs across 16K users.
AI Engineering
The AI PM Maturity Model: Where Most Teams Get Stuck
The AI PM Maturity Model: Where Most Teams Get Stuck | AI PM Portfolio The AI PM Maturity Model: Where Most Teams Get Stuck January 15, 2026 · 18 min read · Product Strategy After 7 years as a product manager across 4 companies -- from enterprise SaaS to an AI-native startup --
Claude Code
What I Learned Running Parallel AI Agents as a Non-Engineer PM
How a non-engineer PM runs parallel AI coding agents in production. Concrete patterns, failure modes, and the 2-agent cap that prevents OOM kills.
Knowledge Graphs
The Immigrant Graph: Why AI Products Need Domain-Specific Knowledge Architectures
The Immigrant Graph: Why AI Products Need Domain-Specific Knowledge Architectures | AI PM Portfolio The Immigrant Graph: Why AI Products Need Domain-Specific Knowledge Architectures September 20, 2025 · 17 min read · Architecture Deep Dive Generic AI models know a little about everything but not enough about anything to be trustworthy for high-stakes
Quality
955 Tests, Zero Flaky Failures: Building Reliable AI Systems
955 Tests, Zero Flaky Failures: Building Reliable AI Systems | AI PM Portfolio 955 Tests, Zero Flaky Failures: Building Reliable AI Systems August 15, 2025 · 15 min read · Engineering Deep Dive We run 955 tests on every push with a zero-flaky-failure rate. The secret is not discipline -- it is architecture.
MCP
The MCP Revolution: Why Interoperability Is the Next Platform Shift
The MCP Revolution: Why Interoperability Is the Next Platform Shift | AI PM Portfolio The MCP Revolution: Why Interoperability Is the Next Platform Shift June 25, 2025 · 19 min read · Industry Analysis The Model Context Protocol (MCP) is the USB-C of AI -- a universal standard for connecting any AI model
Claude Code
AI-Native Development Changed How I Build Products
AI-Native Development Changed How I Build Products | AI PM Portfolio AI-Native Development Changed How I Build Products May 20, 2025 · 18 min read · Practitioner Retrospective AI-native development is not about writing code faster. It is about a fundamentally different relationship between product thinking and production software. Using Claude Code with