Skip to content
Aakash GuptaAakash Gupta

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: https://www.news.aakashg.com/p/claude-code-non-technical-pms Transcript: https://www.aakashg.com/albuquerque-podcast/ --- 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 10:21 - Ads 12:14 - Live demo: connecting Lovable to Claude Code via GitHub 28:37 - Level 3 - Cursor + Vercel for real production 31:02 - Ads 33:22 - 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 01:01:33 - Why 90% of European PMs are still non-technical 01:07:45 - The Monday morning move 01:09:07 - Outro --- 🏆 Thanks to our sponsors: 1. Customer.io: Send smarter messages using your product data - http://customer.io/productgrowth 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: Ariso: Your AI chief of staff for meetings, follow-ups, and coaching - https://ariso.ai/aakash 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 18, 20261h 10mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

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

  1. Non-technical PMs risk becoming “backlog bureaucrats” unless they learn to directly build and ship, mirroring how small AI-native teams operate.
  2. Andre proposes a 4-level framework: start with Lovable for low-risk prototyping, then bridge Lovable with Claude Code via GitHub, then move to Cursor+Vercel for production-grade branching and previews, and finally add agents/skills with a shared CLAUDE.md to scale quality and speed.
  3. A practical demo shows how to bootstrap an app in Lovable, connect it to GitHub, edit the code in Claude Code, merge changes, and visually QA in Lovable before publishing.
  4. Vercel is positioned as the “GitHub-to-users” deployment bridge that enables safe parallel work via branches and preview deployments, reducing fear around production changes.
  5. To avoid “slop,” teams should add guardrails on both ends: stronger infra/security checks before production and stronger discovery/requirements rigor (e.g., JTBD, OST, MoSCoW) before coding.

IDEAS WORTH REMEMBERING

5 ideas

Start with a personal, low-risk project to build confidence.

Andre recommends using Lovable first because it’s less intimidating than an IDE and abstracts away databases/auth; a personal project lets you make mistakes without organizational risk.

Use Lovable as a visual QA layer while Claude Code does the heavy lifting.

By connecting Lovable ↔ GitHub ↔ Claude Code, you can code in Claude Code, merge to GitHub, then instantly see and test changes in Lovable before publishing publicly.

The bridge only works in one direction: bootstrap in Lovable first.

Andre notes you can’t take an arbitrary external repo and “import it into Lovable”; you must start the project in Lovable, then connect it outward to GitHub/Claude Code.

Vercel becomes necessary when you need parallel work and production discipline.

Once you want multiple features in flight, branches, and reliable preview environments, Vercel provides per-branch preview deployments and a clearer path from GitHub to end users than Lovable-as-infra.

Cursor can make Claude Code feel more manageable for non-technical builders.

Andre prefers Cursor’s UI (especially vertical session/tab ergonomics) and the ability to inspect files when desired; Aakash adds Cursor’s free agent can help debug issues if Claude Code setup gets stuck.

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

Because honestly, it's way less scary than just jumping straight into an IDE or jumping straight into, uh, a code environment.

— Andre Albuquerque

It's a accidental, uh, jobs to be done way of using Lovable that I don't think they intended, but it worked really well and it's a great bridge.

— Andre Albuquerque

This is what AI-native teams are doing, is they're working 50% of the time on improving the infrastructure of the machine itself, rather than just tweaking feature by feature, right?

— Andre Albuquerque

Non-technical PMs as builders vs backlog managers4-level builder PM frameworkLovable as beginner-friendly AI IDE and bootstrap toolGitHub as the shared source of truthClaude Code desktop vs Claude Code in CursorVercel preview deployments and branching workflowAgents, skills, and CLAUDE.md team memory/standardsPM-orchestrator agent pattern and division of laborPreventing “slop” through infra checks and better discoveryMonday-morning plan: low-risk repo + oldest backlog item experiment

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