AI-powered product management thinking & operating system. Playbooks, guides, templates, and frameworks that bridge PM theory to daily execution.
This repository also configures its own agents. See what pm-brain tells them →
Agent Claude Code
Mid-tier, read-only independent quality check of a drafted PM artifact (PRD, OKRs, roadmap, North Star, opportunity assessment, one-pager, strategy doc). Use before presenting a non-trivial artifact as done, or when the user asks to evaluate one. Independent so the coach isn't grading its own work.
Agent Claude Code
Fast-tier, read-only scan of PM Brain context. Use proactively before coaching or drafting when the conversation names a stakeholder, initiative, external org, past decision, or company topic — returns a short summary of what the repo already knows plus any contradictions with logged decisions. Keeps the main coaching…
Agent Claude Code
Role-plays a named stakeholder from their PM Brain avatar to pressure-test a plan, message, or decision. Use for "what would [name] say?", panel reactions, or a politics check before a big conversation. Runs isolated so the simulation stays sharp instead of being softened by the coaching voice.