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: 00:00 AI agents can now run a startup workflow 01:23 Subscribe and AI tools bundle 01:55 Claude Code as your designer, developer, and systems analyst 02:43 Gabor’s 21-agent startup team inside Claude Code 04:57 Inside the system analyst agent 05:52 Live demo: zero to TestFlight 08:42 Prompting Claude to define a good system analyst 10:02 Ads 11:53 Building the system analyst workflow 12:24 Why documentation matters: Confluence, Jira, and MCPs 15:38 Why classic PM skills make you a better AI builder 19:22 The scaffolding that prevents AI spaghetti code 22:23 Setting up project-specific agents in Claude Code 26:26 Dictating the full product spec for the hockey rules app 32:26 Ads 35:36 Why dictation changes the quality of AI specs 47:38 Creating the visual direction in Figma Make 56:00 The idea-to-prompt-to-design-to-app workflow 1:06:21 Claude Code starts building the Figma screens 1:24:06 Frontend epics and Figma-linked tickets appear in Jira 1:48:57 The hockey rules AI app is live 1:53:56 Full recap: Claude, Confluence, Figma, Jira, Simulator, TestFlight 2:03:20 Should PMs get AI PM certificates? 2:08:21 How to create a PM portfolio that helps you land top jobs 2:13:32 How to get started building with AI agents --- 🏆 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. --- 👨‍💻 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 27, 20262h 15mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

How to ship an iOS app using Claude Code agents

  1. Gabor shows how he structures Claude Code as a “startup OS” with ~21 specialized agents (system analyst, CTO, designer, test architect, maintainability reviewer, privacy/data council) to mimic a real product team’s division of labor.
  2. The workflow starts with voice dictation in the consumer Claude app to generate a high-context PRD, then uses Atlassian MCP to turn clarified requirements into Confluence documentation and Jira epics/tickets with dependencies.
  3. Design is generated via Figma Make to produce a style guide, then Claude Code uses Figma MCP to create high-fidelity screens and automatically wire them into a clickable prototype, minimizing “generic AI-looking” UI outcomes.
  4. Development is run sprint-by-sprint in parallel (frontend + backend) using the ticket scaffold, with emphasis on maintainability, testing, privacy constraints (no server-side storage of user chat), and secret management (API keys in Firebase Secret Manager).
  5. The live demo culminates in a working Flutter + Firebase iOS app (“Rule Ask”) that uses RAG over the IIHF rulebook and situation book, includes an “observer mode” for transparency, runs in Simulator, and is uploaded to TestFlight, followed by career advice for PMs on building portfolios over collecting certificates.

IDEAS WORTH REMEMBERING

5 ideas

Treat agentic building like running a real software team, not a single prompt.

Gabor’s core claim is that better outcomes come from role specialization (system analyst, CTO, designer, test architect, maintainability reviewer) and structured handoffs, rather than asking one model to “build the whole app” in one shot.

The system analyst agent is the keystone for quality and speed.

He uses the system analyst to force clarifying questions, break requirements into structured documentation, and generate Jira tickets; this reduces ambiguity, prevents rework, and gives coding agents unambiguous tasks.

Up-front scaffolding prevents “AI spaghetti code.”

Gabor argues many “vibe coding” failures are maintainability failures; he adds an explicit maintainability/spaghetti agent to check naming conventions, circular references, and code structure—especially important for non-engineers who can’t easily detect architectural rot.

Context can hurt: too much information leads to compression and missed details.

He notes that when he didn’t break design work into smaller tickets, the design underused parts of the palette from the style guide—his hypothesis is that long context windows still lead to prioritization/compression that drops constraints.

Documentation and ticketing aren’t bureaucracy—they’re the mechanism for repeatability.

By storing decisions in Confluence and turning them into Jira work items (with dependencies and sprint tags), he makes the build reproducible and easier to iterate, similar to how teams maintain velocity over time.

WORDS WORTH SAVING

5 quotes

AI agents are writing PRDs, designing in Figma, writing Jira tickets, and even shipping code all from 1:00 PM at 4:00 AM.

Aakash Gupta

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

Gabor Mayer

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

Gabor Mayer

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

Gabor Mayer

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

Gabor Mayer

Claude Code multi-agent setup (system analyst as hub)Scaffolding: specs, clarifying questions, and dependency mappingAtlassian MCP: Confluence documentation + Jira ticket generationFigma Make style guide → Figma MCP screen creationClickable prototype automation (UX flow architect)Flutter + Firebase architecture and secret managementRAG design: rulebook/situation book embeddings + web fallbackCost controls: per-user word limits and token-awarenessQuality controls: testing plan, maintainability checks, avoiding “vibe code”PM career strategy: portfolios, AI skills gap, certificates vs learning

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