Skip to content

By playing, you agree to uListen's Terms and Privacy Policy and YouTube's Terms of Service.

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.

Andre AlbuquerqueguestAakash Guptahost
May 18, 20261h 10mWatch on YouTube

Summaries, chapters, transcripts, and FAQs on this page are made by uListen, not YouTube.

Great conversations run long. Their best ideas don't have to.

uListen is free on iPhone, iPad, Android, Chrome, and Claude.

See how

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

Read the available transcript
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

Ask ChatGPT about this episode

Get its key ideas, plus a summary of each chapter linked to that point in the video, right in your chat.

  1. Add uListen AI to ChatGPT.

  2. Paste this prompt into a new chat.

    Use uListen AI to give me this episode's key ideas and a chapter-by-chapter summary, with timestamps: https://www.youtube.com/watch?v=bYiXxeinhbg

SPEAKERS

  • Andre Albuquerque

    guest

    Runs a European product builder school (Builders Camp) and teaches practical AI/Claude Code workflows for product managers.

  • Aakash Gupta

    host

    Product-focused podcast host interviewing guests about tooling and workflows for PMs.

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

Get more out of YouTube videos.

Read along on your phone, search it beside the video, or ask your favorite AI app what was said.