Setup call included for 30 days — get AI PM OS installed and skills loading, or money backBuy now: live setup help with George + 30-day up-and-running guarantee
🕹️ prodmgmt.world

AI PM OS for product managers

The AI PM operating system for Claude Code, Codex, Claude Cowork, and Cursor.

Start from a working system — context, workflows, and review standards, without building your own AI stack.

4.9/5 · 703+ PMs

Individual

$99

one-time · one PM

Setup call included

One-time payment · Instant download via Polar

Limited window: setup call included. I get the workspace open and skills loading — or email me within 30 days of purchase for a full refund. After this window, Individual stays $99 self-serve.

Used by individual PMs at these companies

AmazonAppleGoogleMetaCoinbasePinterestEtsyZapier

Everything is already set up to work together.

Tap a layer to isolate · scroll to explode

Calling a skill is not enough. Real PM work needs a workflow.

  • /workflow:strategy

    Core Strategy Development

    What problem you're solving → who it's for → what's unique → competitive position. Produces a strategy kernel.

  • /workflow:research

    Research to Feature

    Transcript cleanup → JTBD extraction → insight clustering → hypothesis → experiment design.

  • /workflow:prd

    PRD Construction

    Draft → strengths reviewer → flaws reviewer → revision loop. Builds a defensible PRD before your team finds the gaps.

Take three complete AI PM plugins for Claude Code. Free.

Real Claude Code plugins you can install and use today. Email the download link — no newsletter signup.

  • Write clearer requirements and decisions with ready PM craft skills
  • Run competitive strategy analysis without building the toolkit yourself
  • Create and critique clear charts with visualization skills that ship

For PMs already using agents on real work.

This is for you

  • You're using AI agents for live PM work — and the outputs still feel generic

    ChatGPT and blank prompts don't know your product. AI PM OS starts from your company, goals, and constraints so drafts sound like your work.

  • You want stronger judgment and faster outputs without building a personal stack

    243 skills, 11 workflows, and review subagents replace the hours you'd spend wiring your own system.

  • You're new in a PM seat and need a competent starting method this week

    Run /start, pick one workflow, and ship a real artifact — strategy kernel, research synthesis, or PRD — without inventing a process from scratch.

  • You want AI speed without the slop

    The system asks before it answers, walks the thinking, and keeps you accountable for the output. Faster drafts. Sharper judgment. Not autopilot.

Skip this if

  • You want a SaaS dashboard with logins and managed seats

    AI PM OS is a Markdown workspace in your editor — files you own, not another admin console.

  • You want a course to watch and forget

    This is where the work happens. Context files need your real product. Workflows need live decisions.

  • You won't use Claude Code, Codex, Cowork, or Cursor

    AI PM OS is built for those editors. If that workflow isn't for you, this isn't the right tool.

  • You want frameworks explained, not applied on real work

    This isn't a PM theory library. It applies the right framework to your situation. Study guides live elsewhere.

Start real work in 10 minutes.

  1. 00

    Download from Polar

    After checkout, Polar gives you an instant download of the complete workspace.

  2. 01

    Open in your AI coding editor

    Open AI PM OS in Claude Code, Codex, Claude Cowork, or Cursor. All skills, knowledge, and context are live immediately.

  3. 02

    Set Your Context

    Run /start once. Fill in your five context files. The OS is now calibrated to your actual situation — in about 5 minutes.

  4. 03

    Ask or Type a Command

    Describe your PM challenge naturally, or use a slash command. The right skill activates and guides the work.

  5. 04

    Build & Save

    PRDs, research notes, decisions, drill logs — everything you produce lives in Work/ and accumulates over time.

Catch weak spots before anyone else sees your work.

12 review agents you can invoke on any doc, plan, or decision — not locked to one workflow. A gut-check before stakeholder review, or a full stack when the stakes are higher.

01

Engineering

Feasibility, effort, technical risk

02

Design

Usability, flows, craft

03

Executive

Strategy fit and the so-what

04

Legal & risk

Compliance, privacy, exposure

05

UX research

Evidence behind the claims

06

Devil's advocate

Attacks the weakest assumption

07

Customer voice

Would a real user care?

08

PRD strengths

Names what the doc gets right

09

PRD flaws

Finds gaps before your team does

Plus 3 orchestrators for longer multi-step runs.

It remembers what matters, so you do not repeat yourself.

Not a notes folder you fill once. PM OS captures as you work, grows a little each session, and recalls the right context when it matters — so knowledge compounds instead of living in scattered docs.

  1. Capture

    decisions & risks, as you work

  2. Grow

    one drip question per session

  3. Recall

    loaded before each workflow

  4. Compound

    every session sharpens the next

Capture

Just say it. It keeps what matters.

Drop an update in plain language. PM OS distills the decisions, risks, and stakeholders — and asks before anything touches your files.

/capture-memory · confirmation-gated · never silent

you, in passing

“Quick update: leadership killed mobile and moved us to retention.”

distilled to
  • decisionMobile cut; focus shifts to retention
  • stakeholderLeadership drove the reprioritization
  • riskIn-flight mobile work now stranded

Use it in Claude Code, Codex, Cowork, or Cursor.

Same skills, same workflows. Lead with Claude Code, or bring whichever tools you already use.

New to the terminal setup? Read the Claude Code for product managers guide.

Claude Code

Starts $20/mo

Autonomous terminal-first coding agent with advanced reasoning

Best for: PMs who want an autonomous agent for deeper, multi-file work.

  • Best-in-class reasoning for complex PM workflows
  • Up to ~1M token context on Max / enterprise
  • Terminal-first, CLI and IDE friendly
Context
Up to ~1M on Max
Interface
Terminal + IDE + desktop
Models
Anthropic only
Learn more

Whichever you pick is a separate subscription, billed by them and not included in AI PM OS. Claude Code and Claude Cowork both need a paid Claude plan. Codex lives in ChatGPT desktop and typically needs a paid ChatGPT plan. Cursor’s free tier works with AI PM OS from day one.

Live Comparison · Same Input

How does it compare to other alternatives?

Most PM OS alternatives · what you usually get

Email 4 of 10 · still on the fence?

Cartoon man with hands clasped pleading 'please please buy my $2000 course'

others lure you in with “free”
to upsell you expensive courses

Most PM OS alternatives

vibe coded

  1. >

    i'm trying to measure the value of engagement in our product

  2. Sure! Engagement is very important. Here are some things to consider:

  3. 1. User research — do you have data on how customers engage?

  4. 2. Engagement is about making something valuable

  5. 3. Don't chase engagement for the sake of engagement

  6. (no company, product, or goal context loaded)

  7. Want me to pretend to use any subagents (they're just markdown files that won't trigger anything)?

AI PM OS · what prodmgmt.world ships

AI PM OS

runs inClaude CodeCodexCoworkCursor

hardened daily in real PM work

  1. >

  2. Recognized as measurement problem

    auto-routed → /measure

  3. Loading your context

    COMPANY ✓ PRODUCTS ✓ GOALS ✓ TEAM ✓

  4. → clarification-chain

    .cursor/skills/clarification-chain/SKILL.md

  5. → fermi-decomposition

    .cursor/skills/fermi-decomposition/SKILL.md

  6. → value-of-information

    .cursor/skills/value-of-information/SKILL.md

  7. → rule-of-five

    .cursor/skills/rule-of-five/SKILL.md

  8. Measurement plan ready for co-review

    Spawning reviewer subagents & validating via knowledge base for any anti-patterns and gotchas

  9. >

Receipts

The difference in experience.

  1. 01

    The right method, every time

    You pick a framework, write a prompt, and hope it sticks.
    Picks the right method for the actual problem in front of you.

  2. 02

    Sticks to your rules

    Reads the rules once. Forgets them mid-conversation.
    Re-checks the rules on every reply, even three hours in.

  3. 03

    Stops you shipping generic slop

    Will write a PRD without knowing your company, users, or product.
    Won’t generate generic output. Asks for the missing context first.

  4. 04

    Frameworks that show their work

    Names a framework. Shows you a paragraph. You’re on your own.
    Pulls the actual framework, applies it to your problem, cites the source.

  5. 05

    Deep memory

    Worse than ChatGPT Projects at remembering your context
    Feels almost too good to be true, surprising every time.

  6. 06

    Picks up where you left off

    Starts from scratch every session. You re-explain the same context.
    Saves & remembers where you work and your current projects. Comes back ready next time.

What PMs say after using it.

Customer testimonial from Riya

“I've been using AI for PM work for over a year and nothing has actually changed how I think until this. The /decisions workflow walked me through reversibility framing on a call I was dreading. I showed up with actual clarity instead of just vibes, and the call felt completely different.”

Riya

Senior PM

Customer testimonial from Tom

“The thing that got me was typing /stakeholder before a brutal exec review and getting a power map, influence tactics, and a pre-meeting script — all grounded in MY product context. So cool.”

Tom

Product Manager

Customer testimonial from Aisha

“I ran the assumption mapping workflow before pitching a new initiative. It identified 4 assumptions I was treating as facts. Two of them were actually testable in a week. I validated one and invalidated the other before writing a single line of the PRD. It finally put things in the right order.”

Aisha

Senior PM

Customer testimonial from David

“Solo PM at a 12-person startup here. No senior PMs to gut-check me, no design partner, no one to push back on my thinking. This is the closest thing I've found to having a CPO in the room. It challenges me instead of just agreeing.”

David

Solo PM, Series A Startup

Customer testimonial from Nisha

“I used the /opportunity workflow to map our entire opportunity space from scratch. It walked me through OST intake, built the tree, and pushed me to defend my target choice with Torres's four-factor framework. My roadmap is more defensible now than it's ever been.”

Nisha

Group PM

Customer testimonial from James

“I typed out a messy problem I'd been stuck on for two weeks and ran it through /strategy. It found the strategic crux in the first output. I had been solving the wrong problem. I cannot overstate how useful that was.”

James

Staff Product Manager

Customer testimonial from Amelia

“What I love is that it's inside Cursor, not another tab I close. It reads my PRD files, my Context folder, my notes — and when I ask it something it's answering about MY product. I stopped context-switching. My whole PM brain lives here now.”

Amelia

Product Manager

Customer testimonial from Marcus

“The /meeting workflow is absurdly good for political situations. Before my last all-hands I ran it and it surfaced two hidden agendas I hadn't named consciously. I went in prepared and walked out with alignment I wasn't expecting.”

Marcus

Director of Product

Why I built the PM system I could not find.

As a product leader, I kept seeing the same thing: PMs shipping AI output without a critical eye, no shared way to write or use skills, no real discovery process.

So I encoded the workflows I actually use — so a junior gets a weapon, and a busy PM can stay fast without the quality falling apart.

Product management shouldn’t be a slog with the odd good day. It should be fun, fast, and smart. Agents are becoming the default workplace — this is the context and skills layer I wish every team already had.

George Nurijanian

8+ years as a Product Leader · Creator of PM OS

Prodmgmt World Limited

@nurijanian
About the maker

I spent years collecting PM frameworks and techniques I never had time to actually use. Bookmarks, Notion databases, saved tweets. When I needed them, I couldn't find them. When I found them, they weren't tailored to my situation.

So I built the AI PM OS for myself first — a workspace that knows my context and surfaces the right skills, frameworks, ideas, articles and workflows at the right moment. It helps me think better and faster, be more creative, align stakeholders, and ship work that actually moves the needle. 700+ PMs use it now. I use it daily.

Questions before you buy?

What exactly is AI PM OS?

AI PM OS is a product management operating system that runs inside Claude Code, Codex, Claude Cowork, or Cursor. After onboarding, you create curated context about your company, product, team, goals, and constraints. From then on, each response starts with your situation instead of a blank prompt.

The workspace includes 243 PM skills, 150+ frameworks, 11 guided workflows, review subagents, and live connectors — one complete operating system for one PM.

What's the difference between a skill, a framework, and a workflow?

A skill is a single AI-invocable PM task — for example, /skill:jtbd-interview runs a structured Jobs-to-be-Done discovery session.

A framework is a structured thinking model a skill applies — for example, one of the 50 prioritization frameworks, each tagged with 'Use When' metadata so the right one activates for the situation.

A workflow is a chained, multi-step process — for example, /workflow:strategy sequences discovery → opportunity → PRD as a connected session, not three separate prompts.

PM OS ships with 243 skills, 150+ frameworks, and 11 workflows — organized so the right one surfaces when a PM needs it.

What's included, exactly?

AI PM OS is a packaged workspace of files and workflows your editor reads automatically. No manual hunting through prompt libraries.

243 PM Skills — across 12 categories including strategy, discovery, prioritization, stakeholder management, and metrics.

150+ Frameworks — organized by product stage: discovery, validation, build, and grow.

50 Prioritization Frameworks — each tagged with "Use When" metadata.

100 Customer Interview Questions — across 6 research categories.

41 North Star Metric Examples — from real growth-stage companies.

25 PM Practice Drills — with session tracking and progress logs.

7 PRD Templates — Amazon PRFAQ, Shape Up pitch, Feature PRD, and more.

11 Guided Workflows — end-to-end motions you can run the same way every time.

260 Curated Lenny Posts — surfaced when you are stuck.

5-File Context System — tell the agents your company, product, team, goals, and constraints once.

Does it interfere with our existing Claude or Cursor setup?

No. AI PM OS is a folder of Markdown files your editors read. It does not replace your company Claude workspace, wipe custom instructions, or force a single vendor lock-in. Open it alongside whatever stack you already run.

Can I get an invoice for procurement?

Yes. Checkout runs through Polar, which issues receipts and invoices for business purchases. If your finance team needs a custom invoice or PO trail, email me at george@prodmgmt.world after checkout and I'll help.

Do I need to know how to code?

No. Claude Code, Codex, Claude Cowork, and Cursor are AI tools — you type plain English. Setup is download the workspace from Polar, open it in your editor, run /start, and answer a few guided questions about your product. No code, no installs beyond the editor.

Do we need a paid plan for Claude Code, Codex, Cowork, or Cursor?

Claude Code and Claude Cowork run on a paid Claude plan (Pro, Max, Team, or Enterprise). Codex lives in the ChatGPT desktop app — a paid ChatGPT plan is typical for daily use. Cursor has a free tier that works with AI PM OS from day one, though most daily users are on Cursor Pro ($20/month). See current pricing: claude.com/pricing · chatgpt.com/pricing · cursor.com/pricing

AI PM OS is a separate license. Your editors are separate products with their own pricing.

Where does our data go? Context files can contain confidential information.

AI PM OS is a local workspace of files on your machine — nothing leaves your computer through me. When you ask Claude Code, Codex, Cowork, or Cursor a question, context is sent to that editor's configured LLM provider under that vendor's terms — the same as any other prompt. Nothing routes through prodmgmt.world. prodmgmt.world is never in the data path and has no subprocessors for this product. If your company restricts AI tool use, AI PM OS inherits those same restrictions.

Need a procurement packet or DPA conversation? Email george@prodmgmt.world.

What if I get stuck setting it up?

For a limited window, Individual includes a setup call with me — I get the workspace open in your editor and the skills loading. You'll get the booking link after checkout.

Outside that window, email me at george@prodmgmt.world and I'll help you get unstuck.

Onboarding is light: download the workspace from Polar, open it in Claude Code, Codex, Cowork, or Cursor, and run /start. The five context files (company, product, team, goals, constraints) are built with guided prompts — not a blank-page homework assignment.

Is there a refund policy for Individual?

Yes. During the setup-call window, if I can't get the workspace open and the skills loading, email me within 30 days of purchase for a full refund.

No hoops, no hard feelings.

How is it delivered? How do updates work?

After purchase you download the workspace from Polar, open it in Claude Code, Codex, Claude Cowork, or Cursor, and run /start. When updates ship, re-download from Polar.

Skills and workflows are maintained against current Claude, Codex/OpenAI, and Cursor releases.

Can I see real skill content before buying?

Yes. A free public sample of the same quality bar lives at github.com/gnurio/nurijanian-skills. Start with make-requirements-great — the full skill source, not a teaser. The full AI PM OS workspace is built to that same bar.

Individual

Start with the system already built.

$99 once

One-time payment · Instant download via Polar