Guides for Product Managers
Complete, free guides on AI applied to product work: the method, the mistakes to avoid and a template to download. Each guide links to its course when you want to go further.
Writing a spec an AI coding agent can execute
How a Product Manager writes a spec that a coding agent like Claude Code, Cursor or Codex can execute without guessing, with a SPEC.md template.
Build a Claude skill, from install to testing
What a Claude Skill is, how to write and install its SKILL.md, make it trigger reliably, test it and audit third-party skills.
Claude Code for PMs: what you can do with it without being a developer
Using Claude Code as a product manager: useful jobs, getting started, a working method, guardrails and working with your engineering team.
Claude Skills or MCP: which one fits which need
The difference between a Claude Skill and an MCP server, how to choose between them, PM use cases and how to combine the two.
MCP for PMs: plug AI into your tools and scope an MCP server
The Model Context Protocol explained for PMs: architecture, use cases, scoping a server, security, evaluation and the mistakes to avoid.
MCP or API: what is the difference, and which one your product needs
MCP and APIs compared for Product Managers: consumer, discovery, contract, auth, costs and security, with a free decision template.
RAG or fine-tuning: picking the right approach for an AI feature
How a product manager chooses between RAG, fine-tuning and a plain prompt for an AI feature, with a downloadable decision grid.
How to evaluate an AI feature: LLM evals explained for PMs
How a product manager evaluates an AI feature before and after launch: test cases, criteria, LLM judge and thresholds, with a PLAN-EVALS.md template.
SQL for PMs: the queries that let you answer your own questions
The SQL a Product Manager actually needs: data model, core queries, common traps, working with AI and read-only access.