Articles and tools for advanced AI-assisted product work. The blog series covers the philosophy, the evolving workflow, and the practical setup. The open source repo has everything you need to get started.
Open Source Toolkit
Product AI Public is a curated collection of prompts, slash commands, and context files for AI-assisted product management. It’s a subset of my personal “second brain” repo, published under an MIT license so others can adapt the system to their own work. Includes opinionated prompts for PRD reviews, OKR checks, product debates, and more, along with the context files that make them actually useful.
Blog Series
1. How I Use AI for Product Work (Dec 2025)
The foundational post. I lay out the philosophy behind my AI setup: context plus constraints, composed on the fly for the task at hand. Covers the folder structure, the layered approach (system prompts, personal context, reference materials), and how I use Windsurf’s @ mention system to turn an LLM into a skeptical colleague rather than a ghostwriter. Includes concrete examples of document review, brainstorming, and technical understanding workflows.
2. How My AI Product “Second Brain” Evolved (Dec 2025)
The system grew. This post covers the move from Windsurf to Claude Code and OpenCode, the introduction of slash commands that remove the friction of composing context manually, and the addition of skills that apply product methodology automatically. Also covers daily and weekly work summaries, calendar briefings, and the practical lessons from building automation that compounds over time.
3. How to Set Up OpenCode as Your Product Second Brain (Jan 2026)
The hands-on companion. A 30-minute setup guide that walks through creating the folder structure, writing your first context file, configuring AGENTS.md, and building three working slash commands: /debate for stress-testing ideas, /okr for reviewing objectives, and /prd for critiquing product requirements documents.
4. Project Brains: Organizing Complex Initiatives (Feb 2026)
Tackles context fragmentation on long-running, cross-team projects. Introduces a dedicated folder structure with a living CONTEXT.md file that tracks status, stakeholders, decisions, and open questions. When the AI can read the same project context you have in your head, its recommendations get grounded in documented reality instead of generic best practices.
5. From Assistant to Collaborator: How My AI Second Brain Grew Up (Mar 2026)
The system crossed a threshold. This post covers the shift from invoking an AI tool to dispatching an AI collaborator, driven by three capabilities: multi-agent orchestration (parallel specialist agents that investigate, synthesize, and validate), cross-session memory (a four-layer system that gives the agent continuity between work sessions), and domain expertise (product-specific skills that encode institutional knowledge about how your products actually work).