The Claude Code Setup for Non-Technical PMs That Nobody Shows You

Most PMs are still bureaucrats stuck in Jira, Linear, and PowerPoints. The best PMs have stopped waiting on engineering and started shipping code themselves. In this episode, Andre Albuquerque (founder of Builders Camp, Europe's largest product builder school with 4,000+ students) walks through his exact 4-level builder PM stack live - Lovable, Claude Code, Cursor, Vercel, and a multi-agent CLAUDE.md setup that AI-native teams actually run. Full Writeup: [VERIFY - newsletter URL] Transcript: [VERIFY - blog URL] --- Timestamps: 00:00 - Intro 02:27 - The biggest problem non-technical PMs face today 04:50 - The 4-level builder PM framework 05:28 - Level 1 - Why you start with Lovable 08:04 - Level 2 - The Lovable + Claude Code bridge 11:28 - Ads 16:26 - Live demo: connecting Lovable to Claude Code via GitHub 28:37 - Level 3 - Cursor + Vercel for real production 30:59 - Ads 33:53 - Why Andre prefers Cursor over Claude Code desktop 35:40 - Mental model: Lovable vs Cursor vs Vercel 41:17 - Level 4 - Agents, skills, and CLAUDE.md 42:50 - The CLAUDE.md memory file explained 45:24 - The PM orchestrator agent pattern 53:26 - How AI-native teams spend 50% of their time 61:33 - Why 90% of European PMs are still non-technical 67:45 - The Monday morning move 69:07 - Closing thoughts --- 🏆 Thanks to our sponsors: 1. Customer.io: Send messages based on what users actually do - https://customer.io 2. Amplitude: The market-leader in product analytics - https://amplitude.com/session-replay?utm_campaign=session-replay-launch-2025&utm_source=linkedin&utm_medium=organic-social&utm_content=productgrowthpodcast 3. Bolt: Ship AI-powered products 10x faster - https://bolt.new/solutions/product-manager?utm_source=Promoted&utm_medium=email&utm_campaign=aakash-product-growth 4. Ariso: Ship AI agents and features faster, with fewer regressions - https://arize.com/?utm_source=aakashgupta&utm_medium=newsletter&utm_campaign=arize_sponsor_ai 5. Product Faculty: Get $550 off their #1 AI PM Certification with code AAKASH550C7 - https://maven.com/product-faculty/ai-product-management-certification?promoCode=AAKASH550C7 --- Key Takeaways: 1. Non-technical PMs are stuck in Jira, Linear, and PowerPoints - Most European PMs are still product owners in disguise, paper-shuffling between strategy and engineering teams. The way out is to actually start building, not to lobby for more autonomy. 2. Start with Lovable on a personal project - Build something for your family, your friends, yourself. The codebase does not need to be pretty. The point is the safety to make mistakes without breaking anything that matters. 3. The Lovable + Claude Code bridge nobody documents - Connect both tools to the same GitHub repo. Write code in Claude Code with all its depth. QA visually in Lovable with its hosted preview. Publish from Lovable's button. The perfect transition layer. 4. Lovable, Cursor, and Vercel are not competitors - Lovable bundles the IDE, the hosting, and the deployment in one product. Vercel exposes the hosting layer so you can run real branches with real preview URLs. Cursor is just an IDE with a generous free tier. 5. Cursor has a free debugging agent - When Claude Code breaks, open a Cursor agent and paste the error. The free agent unsticks you instead of leaving you stuck at step zero. 6. CLAUDE.md is your team's culture - Loaded automatically every session. The first rule should be "for every task, call the PM agent." When you notice yourself fixing the same issue twice, update CLAUDE.md so it never happens again. 7. The PM agent never writes code - The PM orchestrator's only job is to decide which other agent should handle the work. The researcher investigates. The designer proposes. The engineer architects. The implementer writes. 8. Do not copy famous people's skills wholesale - Going on LinkedIn and downloading 100 skills from product celebrities creates more confusion than value. Look at how your real team works. Write each role down as an agent. 9. Fix the agent, not the feature - When something ships wrong, do not patch the output. Identify which agent in the pipeline failed, update its instructions, and run the pipeline again. The next session inherits the fix. 10. The Monday morning move is exactly three steps - Get added as a collaborator on a low-risk repo. Pick the oldest ticket in the backlog. Push a branch and demo by Friday. --- 👨‍💻 Where to find Andre Albuquerque: LinkedIn: https://www.linkedin.com/in/andre-albuquerque/ Builders Camp: https://builderscamp.com Newsletter: https://www.andrealbuquerque.com 👨‍💻 Where to find Aakash: Twitter: https://x.com/aakashgupta LinkedIn: https://www.linkedin.com/in/aagupta/ Newsletter: https://www.news.aakashg.com #BuilderPM #ClaudeCode #AIPM --- 🧠 About Product Growth: The world's largest podcast focused solely on product + growth, with over 200K+ listeners. 🔔 Subscribe and turn on notifications.

Andre AlbuquerqueguestAakash Guptahost

May 17, 20261h 10mWatch on YouTube ↗

WHAT IT’S REALLY ABOUT

Four-level workflow helps non-technical PMs ship real code safely

Non-technical PMs risk becoming backlog bureaucrats unless they learn to directly build and ship with AI-assisted coding workflows.
A four-level progression—Lovable, Lovable+Claude Code via GitHub, Cursor+Vercel, and agent/skills automation—reduces fear while steadily increasing production capability.
A practical bridge is to use Lovable as an easy visual QA and hosting layer while making code changes in Claude Code and syncing them through a shared GitHub repo.
Moving to Vercel introduces standard preview deployments per branch, enabling safer iteration, parallel work, and clearer separation between preview and production.
“Slop” and reliability risks are mitigated by investing in infrastructure checks and by enforcing better problem framing via reusable skills (JTBD, OST, MoSCoW) and agent orchestration (CLAUDE.md + specialized agents).

IDEAS WORTH REMEMBERING

5 ideas

Start building in a zero-risk sandbox before touching company code.

Andre recommends beginning with a personal Lovable project so you can experiment, make mistakes, and learn core concepts (auth, data, UI flows) without organizational risk or permissions.

Use Lovable as a “visual QA + hosting” bridge while coding in Claude Code.

By connecting Lovable to a GitHub repo that Claude Code can also access, you can push changes from Claude Code, then quickly verify UX changes in Lovable before publishing to a public link.

GitHub is the system-of-record that connects your coder (Claude) to your runtime (Lovable/Vercel).

The workflow is: make changes in Claude Code → commit/merge to GitHub → Lovable/Vercel pulls and updates previews; this demystifies “merge/PR/branch” by making it observable through UI updates.

Graduate to Vercel when you need parallel work, safer iteration, and production realism.

Vercel creates preview deployments for each branch, letting you test multiple features in isolation and only merge to main when satisfied—closer to how real engineering teams ship.

Cursor can lower intimidation by making sessions/branches visually navigable.

Andre prefers Cursor’s UI (vertical tab/session management, GitHub sync) while still using Claude Code underneath, helping non-technical builders feel oriented without manually editing code.

WORDS WORTH SAVING

5 quotes

If you look at a lot of companies that have non-technical PMs in teams, they're bureaucrats. They're stuck in Jira, they're stuck in Linear, they're stuck in PowerPoints. They're not actually building. They're not pushing code. They're not adding features. They're dependent on their technical teams to do that.

— Andre Albuquerque

If you're a non-technical PM and your job is still managing backlogs, your job is still writing issues, your job is still creating decks or PowerPoints to present to someone and you're not really building stuff, honestly, you're being left behind.

— Andre Albuquerque

Let's be honest, it's, it's, it's a bit scary. You land here, and it's a bit scary. Like, you don't know what this is.

— Andre Albuquerque

This is what AI-native teams are doing, is they're working fifty percent of the time on improving the infrastructure of the machine itself rather than just tweaking feature by feature, right?

— Andre Albuquerque

One of the things that decelerates people, teams, companies the most is collaboration. And this sounds contrarian, which is like the fact that you have people having to collaborate, it's what slows everything down.

— Andre Albuquerque

Non-technical PMs as “bureaucrats” vs builder PMs4-level builder frameworkLovable for low-risk starts (auth/db handled)Claude Code + GitHub integration and “Lovable as QA/infra”Vercel preview deployments and branching mental modelCursor as IDE wrapper for Claude Code workflowsAgents, skills, and CLAUDE.md as team operating systemPM orchestrator agent patternPreventing “slop” with infra gates + discovery disciplineEuropean PO culture vs US PM expectationsMonday morning plan: low-risk repo + oldest backlog item

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.