How to Become a Builder PM (n8n, Claude Code, OpenClaw)

Mahesh Yadav spent 13 years as a PM at Microsoft, Amazon, Meta, and Google. He left a $1.3M total comp to build on his own. In this episode, he walks through the complete builder PM stack - from building agents from scratch in n8n to automating PRD reviews in Claude Code to delegating research through WhatsApp via OpenClaw - all live on screen. Full Writeup: https://www.news.aakashg.com/p/how-to-become-a-builder-pm Transcript: https://www.aakashg.com/how-to-become-a-builder-pm/ --- Timestamps: 0:00 - Intro 1:53 - What is a builder PM 6:04 - Building an agent from scratch in n8n (live demo) 12:32 - Ads 14:18 - Adding tools and memory to the agent 21:35 - Multi-agent systems and evaluations 29:47 - When n8n falls short 31:16 - Ads 33:39 - When and how to use Claude Code 35:08 - What changed in December 2025 47:17 - PRD review automation in Claude Code (live demo) 1:02:28 - Competitive analysis, mocks, and prototypes 1:05:15 - OpenClaw deep dive and delegation 1:22:06 - How AI PM interviews have changed 1:35:17 - Comp trajectory and why he left Google 1:35:38 - Outro --- 🏆 Thanks to our sponsors: 1. Maven Custom: Get a discount off Mahesh's course with my link - https://maven.com/mahesh-yadav/ai-pm-interview-prep-bootcamp?utm_campaign=aakash-gupta&utm_medium=affiliate&utm_source=maven&promoCode=AAKASHxMAVEN 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. Jira Product Discovery: Prioritize what matters with confidence - https://www.atlassian.com/software/jira/product-discovery 4. NayaOne: Airgapped cloud-agnostic sandbox - https://nayaone.com/aakash/ 5. Product Faculty: Get $550 off their #1 AI PM Certification with my link - https://maven.com/product-faculty/ai-product-management-certification?promoCode=AAKASH550C7 --- Key Takeaways: 1. Builder PM defined - A builder PM talks to customers, figures out what to build, and ships the first version to 10 customers without talking to any developer. The skill is knowing what to build, not knowing how to code. 2. Four agent components - Every agent that works has intelligence (model), tools (actions), memory (session context), and knowledge (your company data). Every agent that disappoints is missing at least one. 3. n8n for foundations - n8n is the best learning tool because you visually see every component of the agent architecture as separate nodes. Build your first multi-agent system and evaluation pipeline here. 4. Claude Code ate three company types - Context companies, action companies, and evaluation companies all got replaced by one agentic loop inside Claude Code. The three pieces collapsed into one tool. 5. Computer control is the real unlock - File system access plus bash commands equals full laptop capability. This is why Claude Code went from coding tool to work operating system. 6. Long-horizon jobs changed the game - AI agents went from 3-minute tasks to 3-6 hour sustained jobs in six months. This turns Claude Code from assistant to autonomous worker. 7. Continuous learning loops - Build a second agent that watches your corrections to the first agent's work. After five repeated patterns, it proposes a skill update. Your tools get better every day. 8. OpenClaw pattern - Delegation through existing channels, full machine sandboxing, model-agnostic. Not a product but a pattern that Google and AWS will copy inside their ecosystems. 9. AI PM interviews changed - At L5 and L6, product sense questions are being replaced with live building exercises and system design for AI architectures. Pull out Claude Code during the interview or you are already out. 10. Compensation trajectory - From $120K at Microsoft to $1.3M at Google over 13 years, doubling every 18 months through AI-focused switches. Left because big companies kill innovation with six-week approval cycles. --- 👨‍💻 Where to find Mahesh Yadav: LinkedIn: https://www.linkedin.com/in/initmahesh/ Maven Course: https://maven.com/mahesh-yadav/genaipm?promoCode=AAKASHxMAVEN 👨‍💻 Where to find Aakash: Twitter: https://www.x.com/aakashg0 LinkedIn: https://www.linkedin.com/in/aakashgupta/ Newsletter: https://www.news.aakashg.com #builderpm #claudecode --- 🧠 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.

Mahesh YadavguestAakash Guptahost

Apr 20, 20261h 36mWatch on YouTube ↗

EPISODE INFO

Released: April 20, 2026
Duration: 1h 36m
Channel: Aakash Gupta
Watch on YouTube: ▶ Open ↗

EPISODE DESCRIPTION

Mahesh Yadav spent 13 years as a PM at Microsoft, Amazon, Meta, and Google. He left a $1.3M total comp to build on his own. In this episode, he walks through the complete builder PM stack - from building agents from scratch in n8n to automating PRD reviews in Claude Code to delegating research through WhatsApp via OpenClaw - all live on screen. Full Writeup: https://www.news.aakashg.com/p/how-to-become-a-builder-pm Transcript: https://www.aakashg.com/how-to-become-a-builder-pm/ --- Timestamps: 0:00 - Intro 1:53 - What is a builder PM 6:04 - Building an agent from scratch in n8n (live demo) 12:32 - Ads 14:18 - Adding tools and memory to the agent 21:35 - Multi-agent systems and evaluations 29:47 - When n8n falls short 31:16 - Ads 33:39 - When and how to use Claude Code 35:08 - What changed in December 2025 47:17 - PRD review automation in Claude Code (live demo) 1:02:28 - Competitive analysis, mocks, and prototypes 1:05:15 - OpenClaw deep dive and delegation 1:22:06 - How AI PM interviews have changed 1:35:17 - Comp trajectory and why he left Google 1:35:38 - Outro --- 🏆 Thanks to our sponsors:
Maven Custom: Get a discount off Mahesh's course with my link - https://maven.com/mahesh-yadav/ai-pm-interview-prep-bootcamp?utm_campaign=aakash-gupta&utm_medium=affiliate&utm_source=maven&promoCode=AAKASHxMAVEN
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
Jira Product Discovery: Prioritize what matters with confidence - https://www.atlassian.com/software/jira/product-discovery
NayaOne: Airgapped cloud-agnostic sandbox - https://nayaone.com/aakash/
Product Faculty: Get $550 off their #1 AI PM Certification with my link - https://maven.com/product-faculty/ai-product-management-certification?promoCode=AAKASH550C7
--- Key Takeaways:
1. Builder PM defined - A builder PM talks to customers, figures out what to build, and ships the first version to 10 customers without talking to any developer. The skill is knowing what to build, not knowing how to code.
1. Four agent components - Every agent that works has intelligence (model), tools (actions), memory (session context), and knowledge (your company data). Every agent that disappoints is missing at least one.
1. n8n for foundations - n8n is the best learning tool because you visually see every component of the agent architecture as separate nodes. Build your first multi-agent system and evaluation pipeline here.
1. Claude Code ate three company types - Context companies, action companies, and evaluation companies all got replaced by one agentic loop inside Claude Code. The three pieces collapsed into one tool.
1. Computer control is the real unlock - File system access plus bash commands equals full laptop capability. This is why Claude Code went from coding tool to work operating system.
1. Long-horizon jobs changed the game - AI agents went from 3-minute tasks to 3-6 hour sustained jobs in six months. This turns Claude Code from assistant to autonomous worker.
1. Continuous learning loops - Build a second agent that watches your corrections to the first agent's work. After five repeated patterns, it proposes a skill update. Your tools get better every day.
1. OpenClaw pattern - Delegation through existing channels, full machine sandboxing, model-agnostic. Not a product but a pattern that Google and AWS will copy inside their ecosystems.
1. AI PM interviews changed - At L5 and L6, product sense questions are being replaced with live building exercises and system design for AI architectures. Pull out Claude Code during the interview or you are already out.
1. Compensation trajectory - From $120K at Microsoft to $1.3M at Google over 13 years, doubling every 18 months through AI-focused switches. Left because big companies kill innovation with six-week approval cycles. --- 👨‍💻 Where to find Mahesh Yadav: LinkedIn: https://www.linkedin.com/in/initmahesh/ Maven Course: https://maven.com/mahesh-yadav/genaipm?promoCode=AAKASHxMAVEN 👨‍💻 Where to find Aakash: Twitter: https://www.x.com/aakashg0 LinkedIn: https://www.linkedin.com/in/aakashgupta/ Newsletter: https://www.news.aakashg.com #builderpm #claudecode --- 🧠 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.

SPEAKERS

Mahesh Yadav
guest
Product manager and builder-focused AI/agents educator; has worked at Microsoft, Amazon, Meta, and Google.
Aakash Gupta
host
Product leader and content creator who hosts interviews about product management and building with modern AI tools.

EPISODE SUMMARY

In this episode of Aakash Gupta, featuring Mahesh Yadav and Aakash Gupta, How to Become a Builder PM (n8n, Claude Code, OpenClaw) explores builder PM roadmap using n8n, Claude Code, and OpenClaw workflows A “builder PM” is framed as someone who can identify customer needs, build a first usable version with modern AI tooling, and reach initial customers without depending on engineers for the initial build.

RELATED EPISODES