Skip to content
Aakash GuptaAakash Gupta

Complete Course: Claude for PMs (Cowork + Code + Dispatch)

Pawel Huryn tracked 74 Anthropic releases in 52 days and built a PM skills marketplace with 10,000 GitHub stars. In this episode, he walks through his complete AI PM operating system live. Cowork, Claude Code, Dispatch, self-improving knowledge bases, MCP connectors, and remote work across all devices. Full Writeup: https://www.news.aakashg.com/p/ai-pms-guide-to-claude Transcript: https://www.aakashg.com/ai-pms-guide-to-claude/ --- Timestamps: 0:00 - Intro 0:54 - Cowork Power User Demo 3:08 - Anthropic's Shipping Velocity 6:07 - Why Stop Using Chat 7:48 - Ads 09:56 - Cowork vs Code vs Dispatch 18:44 - Skills and MCP Connectors 25:03 - PM Skills Marketplace 29:06 - Strategy Canvas Demo 35:14 - Skill Iteration Cycle 40:46 - Why PMs Need Code 44:43 - Building a Second Brain 56:00 - Self-Improving Knowledge 1:10:00 - Dispatch and Remote Work 1:21:07 - PM Mistakes and Future --- 🏆 Thanks to our sponsors: 1. Arize - AI observability and evals: https://arize.com/?utm_source=aakashgupta&utm_medium=newsletter&utm_campaign=arize_sponsor_ai --- Key Takeaways: 1. Stop using Claude Chat as your default. Cowork accesses real files, connects to Gmail and Slack via MCP, and runs parallel sub-agents. Chat does none of this. 2. Skills are the highest ROI investment. Install marketplace baselines, iterate 5-6 times with specific feedback, and Claude rewrites from first principles until 99% accuracy. 3. Progressive disclosure keeps context clean. Agent reads skill names and descriptions first. Loads full instructions only when the task matches. Hundreds of skills, minimal overhead. 4. Your CLAUDE.md should route, not store. Project structure and pointers only. Domain knowledge lives in separate files the agent loads on demand. 5. Build self-improving knowledge with three types. Rules are confirmed and applied by default. Hypotheses are tracked with evidence. Rejected patterns are kept to avoid retesting. 6. The three-line self-improving prompt works for any domain. Review rules before starting. Apply confirmed rules. Update after feedback. Testing, marketing, strategy, whatever. 7. Claude Code adds explorer view, hooks, subagents, and local MCP scoping. PMs need it once their system grows past 50 files. 8. Every Product Compass infographic was built in Claude Code. HTML generation, component library, iteration through conversation, PNG export. Zero code written by the human. 9. Use Agent Browser from Vercel instead of Chrome MCP. Chrome MCP screenshots every 0.5s and burns $100/hr. Agent Browser uses headless mode and is token-efficient. 10. Dispatch lets you run multiple tasks from your phone. Start an infographic, check emails, analyze competitors. Each runs as a separate thread. Your system works while you live. --- 👨‍💻 Where to find Pawel Huryn: LinkedIn: https://www.linkedin.com/in/pavelhuryn/ X: https://twitter.com/pavolhuryn Product Compass: https://www.productcompass.pm PM Skills: https://github.com/phuryn/pmskills Quadathon (May 9th): 60 spots to build with Claude Code + n8n 👨‍💻 Where to find Aakash: X: https://x.com/aakashgupta LinkedIn: https://www.linkedin.com/in/aakashgupta/ Newsletter: https://www.news.aakashg.com #claudecode #aipm --- 🧠 About Product Growth: The world's largest podcast focused solely on product + growth, with over 200K+ listeners. 🔔 Subscribe and turn on notifications to get more videos like this.

Aakash GuptahostPawel Hurynguest
May 13, 20261h 32mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

How PMs use Claude Cowork, Code, Dispatch for 10x workflows

  1. The speakers argue traditional web chat is now a poor default because it cannot persist work across devices, smoothly switch modalities (files → code → artifacts), or maintain long-running, resumable workflows.
  2. Cowork is positioned as the “real work” surface for PMs—handling files, multi-step plans, parallel sub-agent execution, connectors (MCP), and generating polished artifacts like slide decks and infographics.
  3. Claude Code is presented as essential for PMs because product work increasingly touches codebases and complex file hierarchies, and Code offers IDE/terminal-native affordances (repo browsing, hooks, codebase tooling) that Cowork lacks.
  4. They describe building a “second brain for agents” using a lightweight CLAUDE.md plus domain-indexed knowledge files, where the system continually converts examples into rules/hypotheses and updates them via feedback loops.
  5. Dispatch and Web Sessions enable remote, asynchronous work—running multiple background tasks from mobile/desktop—while browser automation should favor token-efficient tooling (e.g., Vercel Agent Browser) over screenshot-heavy Chrome MCP.

IDEAS WORTH REMEMBERING

5 ideas

Treat chat as a last-mile scratchpad, not your main workspace.

Chat is fine for quick one-offs (e.g., grammar checks), but it breaks when you need continuity across devices, long-running tasks, or switching from discussion to files/code artifacts without reloading context.

Use Cowork when the work touches real files or requires multi-step execution.

Cowork can plan and execute sequential steps (e.g., deduping and sorting invoices by month) and produce tangible outputs (PPTX, PDFs, HTML infographics) directly in a project/folder context.

Adopt skills as reusable “procedures,” and rely on progressive disclosure.

Skills load via short descriptions and only expand into detailed instructions when relevant, letting you maintain many capabilities without bloating every prompt; use slash commands when you need deterministic activation.

Iterate skills like you iterate evals: find failure modes, then rewrite the procedure.

Instead of memorizing better prompts, capture feedback after real usage and have Claude refactor the skill from first principles so the same mistake doesn’t recur—this is framed as one of the highest-ROI activities.

PMs can’t avoid Claude Code because engineers and codebases are part of the job.

Cowork is not optimized for navigating large hierarchies or repositories; Code provides explorer-style browsing, codebase-aware tooling, and terminal command execution needed for debugging, instrumentation, and building systems.

WORDS WORTH SAVING

5 quotes

There's no good reason to talk to Claude just over a normal web chat anymore

Aakash Gupta

Most people stay in chat forever. That's like using Photoshop only to crop photos.

Pawel Huryn

Product managers must understand technology. They must get comfortable with, uh, tools that previously were designed for engineers traditionally, so like the terminal.

Pawel Huryn

You cannot be a product manager who only interviews customers and creates items in the product backlog.

Pawel Huryn

There's no excuse to walk into a meeting with a bad presentation anymore. You basically get a McKinsey-level output in a minute or two

Aakash Gupta

Why “stop using chat” as the default interfaceCowork agentic workflows with real files and sub-agentsConnectors/MCP servers and skills (progressive disclosure)PM skills marketplace (plugins, workflows, slash commands)Slide deck generation and artifact quality improvementsClaude Code for codebases, hierarchies, hooks, and terminalsSelf-improving knowledge systems (CLAUDE.md + indexes)Dispatch, Web Sessions, and remote multi-taskingBrowser automation: Chrome MCP vs token-efficient alternativesn8n vs Claude Code: personal vs production automation

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome