How I AI
How I AI

How this PM uses MCPs to automate his meeting prep, CRM updates, and customer feedback synthesis | Reid Robinson (Zapier)

February 2, 2026

AI Summary

5 min read

🎙️ The Voices & The Context

  • The Format: Casual interview podcast with live screen-sharing demos, blending education and practical walkthroughs.
  • The Key Players:
    • Host: Claire Vaux, AI obsessive and product leader, guiding the conversation with sharp questions and her own Zapier expertise.
    • Guest: Reed Robinson, AI Product Manager at Zapier, the "sysadmin of AI" who demos real workflows; fascinating for his hands-on role in AI orchestration across 8,000 apps.
  • The Vibe: Educational yet fun and relatable—intense demos mixed with light-hearted personal anecdotes, sparking "aha" moments for AI tinkerers.

🗝️ Key Themes & Topics

The episode dives into supercharging AI with integrations, focusing on Zapier's MCP (tool servers for AI apps like Claude/ChatGPT). Main topics: demystifying MCPs, automating hated tasks like CRM updates, prepping for meetings/customer work, and personal/family hacks.

Continue reading the full summary in the app — free to try.

Read Full Summary →

Free • No credit card required

What you'll learn

  • 1 (00:00) **🎙️ Introduction: Reed Robinson**
  • 2 (02:41) **Reed's Role and MCP Focus**
  • 3 (04:18) **Zapier MCP Demo and Setup**
  • 4 (09:08) **CRM and Daily Planning Use Cases**
  • 5 (16:22) **Agentic MCPs vs Deterministic Workflows**
  • 6 (25:31) **Customer Feedback and Support Automation**
  • 7 (33:16) **Personal Use Cases Lightning Round**

+ Full timestamped outline available in the app

Show Notes

Reid Robinson, Principal AI Product Strategist at Zapier, shares how he uses Model Context Protocols (MCPs) to automate tedious tasks and create powerful workflows. He demonstrates practical workflows that combine Zapier’s more than 8,000 app connections with AI tools like Claude to create systems that work while he sleeps.


What you’ll learn:

  1. How to use Zapier’s MCP server to create custom collections of tools that work seamlessly with Claude, ChatGPT, and other AI assistants
  2. A workflow for using Claude Projects to provide detailed instructions for tool usage, improving reliability and consistency
  3. How to automate CRM updates and meeting preparation by connecting AI to your calendar, notes, and internal knowledge bases
  4. A system for creating a virtuous cycle of customer feedback by automatically analyzing support tickets and updating knowledge bases
  5. Why thinking about “what your AI could do while you sleep” is a powerful framework for identifying high-impact automation opportunities
  6. Personal use cases, including family calendar management and creating custom songs that demonstrate AI’s ability to bring joy beyond work

Brought to you by:

WorkOS—Make your app enterprise-ready today

Vanta—Automate compliance and simplify security

In this episode, we cover:

(00:00) Introduction to Reid Robinson and his role at Zapier

(02:41) Understanding MCPs as app integrations for AI tools

(04:05) How Zapier’s approach to MCPs works with over 8,000 apps

(09:00) Using Claude Projects to improve tool usage instructions

(12:05) Post-meeting notes management

(15:25) Comparing deterministic workflows vs. agentic instructions

(18:15) Reid’s idea jammer

(20:04) Building a customer interview preparation workflow

(23:10) Using Gemini for processing file-based data

(25:05) Creating a virtuous cycle of customer feedback analysis

(29:16) The “if you could run ChatGPT in your sleep” framework

(31:48) Quick recap

(33:03) Personal use cases

(37:16) Using Notebook AI to prepare personalized interview prep

Tools referenced:

• Reid’s Resources for How I AI: https://how-i-ai-reid.zapier.app/resources

• Claude: https://claude.ai/

• Zapier: https://zapier.com/

• Zapier MCP: https://zapier.com/mcp

• Granola: https://www.granola.ai/

• Coda: https://coda.io/

<
How I AI

More from this podcast

How I AI →