A versioned product-management source toolkit
A versioned product-management toolkit made of skill definitions, orchestration code, evaluation rubrics, examples, APIs, and platform adapters. It is an inspectable working environment, not evidence that generated artefacts are automatically correct.
Source toolkit under active development
Source through 2026-07-27
Inspectable artefacts
Explicit claim boundary
Source evidence
A versioned product-management toolkit made of skill definitions, orchestration code, evaluation rubrics, examples, APIs, and platform adapters. It is an inspectable working environment, not evidence that generated artefacts are automatically correct.
Repository evidence is not client, deployment, certification, or outcome evidence.
The Problem
Why product teams can't keep up
Product managers can lose substantial time recreating PRDs, stories, roadmaps, and planning material instead of testing assumptions and aligning decisions.
Artefact quality varies when teams lack shared frameworks, rubrics, and reusable examples. Important reasoning can remain implicit and difficult to review.
Product context is often distributed across planning, design, engineering, and communication tools. Each hand-off creates a risk that assumptions and evidence lose their traceability.
Growing teams need reusable product discipline without assuming that generated artefacts can replace accountable product leadership.
Capabilities
10 pillars of AI-powered product management
Source scope only: a card can describe implemented code, a documented adapter, or a configured workflow. It is not a statement that a production service is active.
320+ expert-grade PM skills across 14 disciplines — strategy, GTM, discovery, analysis, planning, AI/ML, platform, enterprise, and growth. Each skill includes named frameworks with book citations, anti-patterns, and quality checklists.
10 specialized AI roles — analyst, architect, developer, UX designer, copywriter, tester, security, DevOps, scrum master, and business analyst. Each role brings discipline-specific expertise to your product process.
5-stage framework from UC Berkeley executive programs: Discovery → Insights → Architecture → Experiment → Deploy. PM approval gates control advancement. Three modes: fast, standard, and careful.
6 pre-built skill chains — discovery-to-PRD, GTM launch, churn-to-retention, strategy-to-roadmap, sprint cycle, and new feature. Each workflow passes context between stages for coherent end-to-end output.
PM Company OS — describe an idea, and AI agents across disciplines execute in sequence. PM approves at gates, artefacts version in git, and feedback loops improve output quality over time.
Write back to your existing stack: Notion pages, Linear issues, Jira tickets, GitHub releases, Figma specs, Miro boards, Slack digests, and Confluence wikis. Generate artefacts and push them where your team already works.
Embed your PM playbooks, interview transcripts, and competitive intelligence into a retrieval system. Skills reference your institutional knowledge — not generic advice — with evidence quality tiering and staleness warnings.
Source-controlled quality checks, selected evaluation rubrics, and benchmark artefacts make parts of the output reviewable. Coverage and model-judge reliability remain bounded.
Runs on 5 AI platforms without modification: Claude Code (plugin), Claude Desktop (MCP), ChatGPT (Custom GPT), Mistral AI (Agents API), and custom HTTP API. Use your preferred AI assistant.
The repository contains container, orchestration, cloud-template, audit, and service-level design surfaces. Templates are not evidence of a production deployment, security posture, or compliance status.
Tech Stack
Named technologies identify repository dependencies or adapter surfaces; they do not assert a live integration or deployment.
Python 3.12+, FastAPI, Click CLI, Redis caching, Pydantic v2, litellm multi-provider abstraction
Claude (Sonnet/Opus), GPT-4o, Mistral Large, Ollama (local), 3-tier model routing, RAG with FAISS + sentence-transformers
React 18, Vite, Tailwind CSS, skill browser UI, brief input, output panel, history panel
Notion (pages), Linear (issues), Jira (tickets), GitHub (releases), Figma (specs), Miro (boards), Slack (digests), Confluence (wikis)
Docker Compose (5 services), Kubernetes Helm, AWS ECS Fargate, GCP Cloud Run, nginx reverse proxy, API key scoping
Pytest (13-check skill audit), LLM-judge rubrics (6 artefact types), 15 expert-quality benchmarks, hypothesis-based testing
Pricing
Contact me to learn how LaunchpadOS can transform your product management practice with AI-powered skill execution.
See how 320+ expert PM skills, 10 virtual team roles, and the Berkeley Innovation Pipeline can turn one PM into an AI-augmented product team. I'll walk you through a personalised demo.
Beyond LaunchpadOS, I offer hands-on consulting to accelerate your product management practice — from AI strategy to team training.
Four weeks to a strategy document, a business case, an ROI model, and a 12-month execution plan — scoped for industrial operators where OEE, safety-regime timelines, and physical-system procurement cycles are the real constraints, not just board optics
Most AI pilots stall before production. Get the playbook for the ones that ship.
Unsubscribe anytime. No spam, ever.
LaunchpadOS Squad is the consulting offer that runs this platform for you. An AI-augmented product team ships V1 in 8–12 weeks, or runs as monthly capacity alongside yours. The platform is installed in your environment and yours at handover.
See the LaunchpadOS Squad service