Skip to content
Aakash GuptaAakash Gupta

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 ↗

CHAPTERS

  1. Why “builder PM” is more than using trendy tools

    Mahesh and Aakash frame the moment: PMs are increasingly expected to prototype, automate, and even push code. They open by rejecting the misconception that simply using Claude Code or OpenClaw makes you a builder PM—what matters is responsibility for outcomes and the ability to ship first versions quickly.

  2. Defining a builder PM: customer clarity + first-version shipping without a dev team

    Mahesh defines a builder PM as someone who can work backwards from customers and produce a usable first version—often to the first ~10 customers—without relying on dedicated engineering. The role is positioned as “diffusing AI benefits into the economy,” not just managing roadmaps.

  3. Agent fundamentals via n8n: models vs scaffolding (knowledge, memory, tools, guardrails)

    Using a “human development” analogy, Mahesh breaks down agents into the intelligence layer (model) plus scaffolding: knowledge/context, memory (state), tools (actions), and guardrails. He argues builder PMs must understand these primitives to debug and scale agent behavior.

  4. Live demo: build a basic n8n agent from scratch (and watch it fail without context)

    Mahesh creates a minimal n8n AI agent with a chat model and tests it with general questions, then with a current-events query to show knowledge cutoff limitations. The point: a bare model is useful but insufficient for real-world tasks that require fresh information.

  5. Adding tools and memory: search augmentation + conversational continuity

    He adds a web search tool (Tavily) to retrieve up-to-date information and then shows the next failure mode: without memory, the agent can’t reference prior turns. Adding a memory component enables follow-up questions and continuity without re-calling tools every time.

  6. Company knowledge with RAG: ingest contracts, chunking, embeddings, retrieval

    Mahesh demonstrates building a knowledge base by uploading a contract (MSA), chunking it, generating embeddings, and storing it for retrieval. The agent can then answer contract-specific questions grounded in company documents instead of generic legal advice.

  7. Multi-agent workflows and “email-to-analysis” automation

    Moving beyond a single agent, Mahesh shows a multi-agent system that triggers from Gmail: send an email request and receive structured contract-risk analysis back automatically. This illustrates end-to-end orchestration: ingestion, retrieval, analysis, and delivery through real channels.

  8. Evals and ground truth: measuring agent quality before it gets you fired

    Mahesh emphasizes that agents don’t self-police; humans bear the consequences. He demonstrates creating ground-truth labels (e.g., lawyer-reviewed contract terms) and running evaluation workflows to score risk detection and modification quality.

  9. Where n8n falls short: scaling beyond the first customers and into production

    n8n is positioned as ideal for learning and early traction, but it becomes limiting for collaborative development, testing, containerization, and production operations. Mahesh highlights the lack of a clean path from visual workflows to code-based teamwork.

  10. When to use Claude Code: from workflows to code + reusable skills

    Mahesh recommends using n8n briefly, then moving to Claude Code (and tools like Cowork) to combine delegation with real codebases. Claude Code is framed as a universal work engine: if it can code reliably, it can perform many knowledge-worker tasks reliably too.

  11. What changed in Dec 2025: agent loop productization + computer control + long-horizon jobs

    Mahesh explains the shift: Anthropic’s agent loop (context → actions → evals) became a product surface, supercharged by computer control (files + bash + browser) and longer-horizon models. This collapses entire categories of point solutions (context companies, action companies, eval tooling) into one platform.

  12. Live Claude Code demo: PRD review automation + continuous learning from your edits

    Mahesh shows a PRD/two-pager review workflow: Claude applies a checklist, inserts comments directly into the document, and produces an annotated output. He then layers on a learning system that monitors his manual edits, writes “learner.md,” and suggests checklist updates after repeated patterns—creating a human-in-the-loop improvement flywheel.

  13. Beyond PRDs: competitive analysis, mocks, prototypes, and dashboards in one compressed cycle

    Mahesh outlines how Claude Code can cover the full PM cycle: competitive research, mock creation, prototype building, and analytics/dashboarding. The core claim is time compression: what used to take months can be reduced dramatically when one tool spans research-to-build-to-measure.

  14. OpenClaw deep dive: delegation through channels + sandboxed machines + model flexibility

    OpenClaw is presented as an open-source pattern built on an agentic loop, emphasizing delegation (do work asynchronously) and channel integration (WhatsApp/Slack/Signal/etc.). It runs in a controlled environment (e.g., Mac Mini or VM) and can swap models (including open-source) to avoid vendor limits.

  15. Enterprise reality: security constraints, sandboxing as the next frontier, and AI PM interviews

    They discuss why big companies can’t simply deploy OpenClaw broadly and argue the future is provider-controlled sandboxing (secure VMs) that reproduce issues, test fixes, and return solutions safely. Mahesh closes with how AI PM interviews are changing—more case studies, more system design, and an expectation that candidates use modern tools during the process—plus his personal comp trajectory and why he left big tech to build independently.

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