Aakash 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: [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.

AAAndre AlbuquerqueguestAGAakash Guptahost

May 17, 2026·1h 10m·Watch on YouTube ↗

📖 CHAPTERS

1. 1

   Why non-technical PMs are becoming “bureaucrats” (and why it’s risky)

   Andre argues many non-technical PMs are trapped in Jira/Linear/decks and dependent on engineers to build, which slows teams and reduces PM impact. He contrasts this with AI-native companies where everyone—including CEOs—contributes to shipping software. The core premise: PMs who don’t build will increasingly be left behind.

2. 2

   The 4-level “Builder PM” framework (overview of the path)

   Andre introduces a stepwise ladder from zero-code comfort to production-grade shipping. The framework is designed to reduce fear and incrementally add tooling and responsibility. Each level adds a new layer: prototyping, code control, deployment, then automation via agents.

3. 3

   Level 1 — Start with Lovable to build confidence (personal, low-risk projects)

   Andre recommends beginning with Lovable because it’s less intimidating than an IDE and abstracts away backend concerns like auth and databases. He emphasizes starting with a personal project to reduce pressure and encourage experimentation. The goal is to learn by building, not to perfect code quality on day one.

4. 4

   Level 2 — The Lovable + Claude Code “bridge” via GitHub (use Lovable as QA/hosting)

   Andre explains an “accidental” but powerful workflow: use Claude Code to edit the codebase, push changes to GitHub, and have Lovable pull updates so you can visually QA and publish without managing deployment tooling. This creates a gentle transition into real code workflows while keeping the comfort of Lovable’s UI and hosting. It also reframes Lovable as a preview/QA environment during the learning phase.

5. 5

   Live demo — Bootstrapping in Lovable, then wiring GitHub + Claude Code step-by-step

   They walk through creating a simple Lovable app, connecting it to GitHub, ensuring Claude Code has GitHub integration enabled, and then selecting the new repository in Claude Code. Andre demonstrates a design-system change (color theme) and shows it appearing back in Lovable after merge. The demo makes the bridge workflow concrete and repeatable for non-technical PMs.

6. 6

   Non-technical-friendly Git basics: branches, PRs, and “merge to main” without fear

   Aakash gives a simplified explanation of the standard engineering workflow (branch → PR → review → merge). Andre clarifies that for personal projects you can skip reviews and merge quickly, but in company contexts you’ll need to follow team pipelines. The key takeaway is PMs don’t need to master Git upfront—Claude can interpret intent—but understanding the mental model helps.

7. 7

   Publishing and preview links in Lovable: QA before going public

   Andre shows that pushing code to GitHub updates Lovable’s preview environment, but the public URL updates only after you publish. He highlights using preview links for testing across devices and sharing with others for feedback. This reinforces Lovable’s role as a training-wheel hosting layer for early-stage builder PMs.

8. 8

   Level 3 — Moving off Lovable: Cursor + Vercel for production workflows

   Andre explains the transition to Vercel once you need faster iteration, safer parallel work, and proper branching workflows. He shows Vercel deployments where each deployment corresponds to a branch/feature and provides preview URLs. Cursor becomes the preferred IDE interface for managing multiple Claude Code sessions more comfortably.

9. 9

   Mental model: Lovable vs Claude Code vs GitHub vs Vercel (what each tool actually is)

   Aakash and Andre clarify roles in the stack to reduce confusion: Claude Code is where you generate/edit code, GitHub is where the code lives, and Vercel bridges the repository to live deployments for users. Lovable is normally an AI builder/IDE, but can act as simplified hosting/QA in levels 1–2. The emphasis is pragmatism over deep technical mastery.

10. 10

    Why Andre prefers Cursor over Claude Code desktop (usability + multi-session work)

    Andre explains that Cursor’s interface (notably vertical tabs and project ergonomics) feels less intimidating and supports working across multiple parallel sessions/epics. Aakash adds practical reasons: Cursor can help debug Claude Code setup issues and has easy GitHub syncing. The chapter frames tool choice as personal “comfort engineering” for non-technical builders.

11. 11

    Level 4 — Agents, skills, and CLAUDE.md: building a “machine that builds”

    Andre introduces the quality/speed scaling layer: a shared repo of agents and skills plus a CLAUDE.md file that encodes working rules and values. The goal is to prevent “slop” from vague prompting by enforcing process, roles, and checks. This moves the PM from one-off prompting to an orchestrated pipeline that reliably produces better output.

12. 12

    The PM orchestrator agent pattern: how agents get called and coordinated

    They break down what “agents” really are: not autonomous bots acting randomly, but callable role modules that Claude can invoke based on rules. Andre’s setup forces every task to start with a PM orchestrator agent, which then delegates to specialist agents (design, engineering, discovery). This mirrors how a real product team coordinates work, but inside the coding workflow.

13. 13

    Avoiding “slop”: infra/security checks + better discovery rigor (and why collaboration shifts)

    Andre argues you avoid bad AI-shipped code through two controls: stronger infra/security gating and stronger up-front problem framing. He also claims collaboration is often misapplied—teams collaborate too much during execution (dependencies) and too little during discovery and delivery. The AI-native model pushes collaboration to the beginning and end, enabling individuals to execute independently in the middle.

14. 14

    Europe vs US PM culture + the Monday morning move to become a builder PM

    Andre critiques European product-owner-heavy cultures that push PMs into delivery management and reduce true team ownership. He encourages PMs to create small pockets of change: bring engineers/designers into discovery, adjust rituals, and start experimenting with building. For an actionable Monday plan, he suggests getting access to a low-risk repo, picking the oldest backlog item, and building it with Claude Code as a demo of the new power dynamic.