Articles on autonomous PM workflows, context engineering,
and Claude Code for product teams.
Rolling out AI to a PM team fails the same way every time: one PM figures it out, the system doesn't transfer, and everyone else falls back to their old workflow. Here's how to build AI into the team — not just hand it to individuals.
Most PMs are using AI. Very few are getting real leverage from it. The gap isn't about prompting skill or model capability — it's about whether you have a system. Here's what separates the 10% from the 90%.
Stop reading listicles. The PM AI Stack is a 3-layer framework for choosing the right AI tools based on your team size, maturity, and actual workflow gaps — not feature checklists.
The best PM frameworks — Torres, Cagan, Biddle, RICE, JTBD — lose their value when applied inconsistently. Here's how embedding them in AI skills produces better outputs than manual application ever did.
MCP lets Claude Code connect directly to Linear, Notion, Slack, PostHog, and your CRM. Here's the PM's guide to setting up each integration and the workflows they unlock.
There are 6 levels of AI maturity in product management. Most teams are stuck at Level 1 or 2. Here's the full breakdown — and how to move up.
Set up automated weekly competitive intelligence briefings using AI agents in Claude Code. Stop letting competitor moves slip through the cracks — get a structured briefing every Monday without manual research.
Most PMs think agentic AI means smarter chatbots. It doesn't. Here's what agentic PM workflows actually look like — from competitive analysis to research synthesis to autonomous intelligence — with real examples from 70+ working skills.
Two competing product teams in the same market. One runs a PM operating system. One does not. Here is what happens at Day 1, Month 1, Month 3, Month 6, and Year 1 — and why the gap between them only widens.
MCPs look great in demos. But at team scale, they cost 6x more in token overhead and add failure points. Here's why production PM teams switch to API skills.
How AI agent teams process user interviews in parallel — turning 10 transcripts into structured opportunity trees, theme maps, and evidence tables in 15 minutes instead of 10 hours.
Every Claude Code setup guide is written for one PM. This is the guide for rolling it out to a product team — shared context, consistent skills, and onboarding that takes 30 minutes instead of 3 weeks.
Anthropic launched scheduled tasks and /loop in Claude Code in March 2026. This turns PM operating systems from toolkits into runtimes. Here's what autonomous PM workflows look like in practice — and how to set up your first one.
Most AI-generated PRDs are generic because the AI knows nothing about your product. Learn why persistent context — not better prompts — is the fix, and how to generate PRDs that your engineering team can actually build from.
The best engineering CLAUDE.md files include workflow orchestration, self-improvement loops, and verification gates. Here's what that same rigor looks like for product management.
Ben Horowitz wrote 'Good Product Manager, Bad Product Manager' in 2002. Here's the 2026 version — what separates great AI product managers from the rest, written in the same spirit as the original.
A PM operating system is the persistent infrastructure layer — context, skills, integrations, and intelligence — that makes every PM on your team consistently productive. Here's what it includes, how it differs from PM tools, and how to evaluate whether your team needs one.
I used ChatGPT for everything — PRDs, competitive analysis, interview synthesis. Then I switched to Claude Code. The difference isn't the model. It's persistent context, file-based output, and agent teams that changed how I do PM work.
Context engineering is the practice of structuring product knowledge so AI produces specific, actionable output. Learn why it matters more than prompt engineering for PMs, and how to build your own PM context system.