How this PM uses MCPs to automate his meeting prep, CRM updates, and customer feedback synthesis
Reed Robinson, a product manager at Zapier, demonstrates how Model Context Protocols (MCPs) can automate tedious professional workflows like meeting prep, CRM updates, and customer feedback synthesis. Robinson shows practical implementations using Claude with Zapier MCPs to give AI tools access to knowledge and actions across 8,000+ integrated applications, turning repetitive tasks into seamless automated processes that run in the background.
Key takeaways
- • MCPs are essentially app integrations for AI tools that provide both knowledge access and the ability to take actions within connected applications.
- • Using Claude Projects with detailed instructions on tool-calling sequences and order significantly improves execution quality for complex workflows like CRM updates and meeting prep.
- • The "perfect team with infinite time" framework helps identify high-impact AI use cases—ask what your ideal support team or sales team would do with unlimited resources, then automate it.
- • Google Gemini excels at processing file-based contexts (PDFs, HTML, video, audio) with lower token usage, making it ideal for document-heavy workflows like analyzing meeting research.
- • Building feedback loops that automatically surface FAQ candidates from support tickets and chatbot conversations maintains high-quality knowledge bases without manual overhead.
- • Personal use cases like family calendar synchronization and interview preparation via NotebookLM audio overviews demonstrate how MCPs can improve both productivity and relationships.
Recommendations (15)
"MCPs, I will say, still, I think, are both kind of very hyped and underutilized by people. It really just is like app integrations for your AI tools."
Reed Robinson
"If it's really not my Google calendar, it like doesn't exist. And it uses the various like find and update and create actions for Google Calendar through Zapier MCP and just like does all of it."
Reed Robinson · ▶ 33:51
"We used Databricks which houses like a lot of our data and makes that usable. And so they built like this whole series of things that allows like just simple lookup."
Reed Robinson · ▶ 21:27
"Notebook LM I use personally for learning. I put like a lot of things in it to learn, but I got one that I got a lot of value from with my wife."
Reed Robinson · ▶ 37:22
"One of the tricks for anybody listening, check out Claude projects. One of the things that you can do in Claude projects is provide very like detailed instructions for use cases."
Reed Robinson · ▶ 9:28
Mentioned (2)
More from these creators
Claude Code for personal productivity: a step-by-step tutorial | Hilary Gridley
How Stripe deploys 1,300 AI-written PRs per week
How Microsoft's AI VP automates everything with Warp | Marco Casalaina
From journalist to app developer using Claude Code
How Figma engineers sync designs with Claude Code and Codex
5 steps to generate consistent brand images with Midjourney