Skip to content
Aakash GuptaAakash Gupta

He Uses 7 Claude Code Agents to Build Apps with 0 Employees

Gabor Mayer is a PM at Google who runs a 21-agent Claude Code development team. In this episode, he walks through a live demo building a production mobile app from zero to TestFlight - Confluence for specs, JIRA for tickets, Figma for design, and Claude Code for development. Full Writeup: https://www.news.aakashg.com/p/how-to-build-a-full-ai-dev-team Transcript: [VERIFY - transcript URL] --- Timestamps: [ --- 🏆 Thanks to our sponsors: 1. Maven Custom: Go from PM to AI builder with Cloud Code - https://maven.com/gabor/productbuilder 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. Testkube: Leading test orchestration platform - http://testkube.io/ 4. Land PM Job: 12-week experience to master getting a PM job - https://www.landpmjob.com/ 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. One-prompt vibe coding fails because of context compression - When you give one agent one massive specification, the model silently drops details it considers lower priority. Your color palette, edge cases, and security requirements disappear. Break work into smaller scoped tasks with dedicated agents. 2. The system analyst agent is the most important agent in any AI dev team - It asks clarifying questions one at a time, documents decisions in Confluence, and maps dependencies before code is written. Without it, every agent operates on partial context. 3. Dictation produces 5x more specification detail than typing - Use voice tools like Super Whisper to describe your app requirements. Even imperfect dictation captures more nuance than careful typing. The AI handles the interpretation. 4. Reusable agents encode institutional knowledge - Every painful lesson, API workaround, and MCP quirk gets saved in the agent markdown file. The next project starts from a position of strength rather than from zero. 5. Attach screenshots to every front-end development ticket - Without visual references, coding agents default to generic AI aesthetics. The Figma link or screenshot is what ensures your brand design actually shows up in the code. 6. Build a Spaghetti Agent for code quality - A dedicated code maintainability agent checks naming conventions, circular references, and comment quality after every sprint. It catches structural problems a PM would never spot. 7. The coding phase is the fastest part of building - Specification, documentation, design, ticket creation, and team review take longer than the actual code generation. Do not skip the front-end work. 8. Sprint organization with dependency mapping is essential - Use tags as a workaround for Atlassian MCP limitations. Map dependencies between tickets so agents build features in the right order. Without sprints, agents build on top of code that does not exist yet. 9. Product specification quality determines product quality - The house analogy holds. If you describe a three-bedroom house to one contractor and walk away, the result will disappoint. A complete spec with a full team review produces dramatically better output. 10. PMs should build to understand how agents work - If your product's future is agentic, you need firsthand experience with agent limitations, tendencies, and failure modes. Building is the fastest way to develop that intuition. --- 👨‍💻 Where to find Gabor Mayer: LinkedIn: https://www.linkedin.com/in/mayergabor/ Maven Course: https://maven.com/gabor/productbuilder X: https://x.com/gabor_pm 👨‍💻 Where to find Aakash: Twitter: https://www.x.com/aakashg0 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 GuptahostGabor Mayerguest
Apr 26, 20262h 26mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

One person builds and ships apps using Claude Code agents

  1. Gabor Mayer outlines a “startup in Claude Code” setup with ~21 specialized agents (system analyst, CTO, designer, test architect, maintainability, privacy/data council) modeled after a real software team.
  2. He shows why upfront scaffolding—clear specs, documentation, and stepwise clarification—reduces “vibe coding” pitfalls like spaghetti code, missing edge cases, and unmaintainable architectures.
  3. The live build walks from voice-dictated requirements to Confluence documentation and then to design creation via Figma Make plus automated screen building and prototype wiring inside Figma using MCP integrations.
  4. The workflow then generates Jira epics/tickets with design links/screenshots, organizes work into sprint-like batches, and parallelizes frontend/backend execution with multiple agents.
  5. The demo culminates in a working Flutter + Firebase app with RAG over IIHF rule documents, an “observer mode” for transparency, and an uploaded TestFlight build, plus practical warnings about permissions, secrets, and App Store review latency.

IDEAS WORTH REMEMBERING

5 ideas

Treat agentic building like managing a real team: roles, artifacts, and handoffs.

Gabor’s biggest quality gains come from defining specialized roles (system analyst, test, maintainability, privacy) and letting each agent review work from its perspective before coding starts.

Specification quality is the main determinant of output quality—even with AI.

He argues “good spec → good product,” and demonstrates using clarifying questions one-at-a-time to avoid ambiguity and overwhelm while steadily converging on implementable requirements.

Documentation is not bureaucracy; it’s how you avoid unmaintainable “vibe code.”

By generating Confluence pages first and converting decisions into structured tickets, he reduces code drift and makes the project replicable and maintainable over time.

Context overload degrades results; break work into tickets to preserve fidelity.

When too much style/context is passed at once, details get “compressed” and ignored (e.g., unused color palette); ticket-level granularity with screenshots/links keeps implementation aligned with design intent.

MCP connectivity is a practical moat for tool choice in an agentic world.

He chose Atlassian partly because the MCP connector lets Claude read/write docs and tickets; similar reasoning drives using Figma MCP and Chrome DevTools MCP to execute UI work end-to-end.

WORDS WORTH SAVING

5 quotes

Vibe coding is just the rebranding of unmaintainable, low-quality source code.

— Gabor Mayer

If you build a good specification and you break it down appropriately, then you will have a much better quality end product.

— Gabor Mayer

As long as it operates inside of the development folder, you are good. But as soon as it would operate outside, then it would be something to watch more closely.

— Gabor Mayer

In two years, the gap will be so big between those who build and those who are just productivity AI users that it will be very hard to catch up.

— Gabor Mayer

Pay for a course for the knowledge, not for the certificate.

— Gabor Mayer

Multi-agent “company” inside Claude CodeSystem analyst as the hub for specs and ticketsMCP integrations (Atlassian, Figma, Chrome DevTools)Confluence documentation and Jira ticket automationDesign pipeline: inspiration → Figma Make style guide → Figma screensRAG architecture: rulebook/situation book embeddings + web fallbackCost/abuse controls: token/word limits, local-only chat storage, secrets management

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