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

Overview

Shownote

Highlights

Transcript

Chapters

Pins

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

How I AI

Feb 02
How I AI

How I AI

Feb 02
OverviewShownoteHighlightsTranscriptChaptersPins

Shownote

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 w...

Highlights

Reid Robinson, Zapier’s Principal AI Product Strategist, explores how Model Context Protocols (MCPs) transform AI from passive chatbots into proactive, task-executing agents—enabling automation that runs continuously and reliably across real-world applications.
00:00
MCPs are app integrations for AI tools that enable agentic instructions instead of just deterministic workflows
02:41
MCPs are hyped but underutilized, and listeners should identify what they'd want their AI tools to do and find an MCP for that
04:07
Zapier MCP exposes 8,000 apps and 30,000 actions for AI agents
09:02
MCPs are underappreciated by customer-facing teams for updating CRM records
14:57
Users train models to populate unique CRM fields because base models don’t know custom fields or choices.
15:26
MCP requires AI apps to have tools, knowledge, and action capabilities
18:15
Vanta helps AI startups achieve security, compliance, and transparency
22:49
Databricks lookups in MCP tools for Claude usually take too long
23:10
Gemini excels with file-based data like PDFs, HTML, video, and audio
28:05
Zapier automates FAQ proposal from closed tickets and chatbot transcripts, requiring only human review before publishing
29:16
Think about what a perfect team with infinite time would do to find AI use cases, not just how to do existing tasks faster
31:52
MCPs on Zapier offer custom tools for calling and focus on avoiding disliked tasks like CRM updates
35:31
Suno v5 lets kids learn prompting by co-creating songs from meeting transcripts and incident post-mortems
37:16
Notebook AI helped Anna prepare for job interviews and land her ideal job

Chapters

Introduction to Reid Robinson and his role at Zapier
00:00
Understanding MCPs as app integrations for AI tools
02:41
How Zapier’s approach to MCPs works with over 8,000 apps
04:05
Using Claude Projects to improve tool usage instructions
09:00
Post-meeting notes management
12:05
Comparing deterministic workflows vs. agentic instructions
15:25
Reid’s idea jammer
18:15
Building a customer interview preparation workflow
20:04
Using Gemini for processing file-based data
23:10
Creating a virtuous cycle of customer feedback analysis
25:05
The “if you could run ChatGPT in your sleep” framework
29:16
Quick recap
31:48
Personal use cases
33:03
Using Notebook AI to prepare personalized interview prep
37:16

Transcript

Claire Vo: MCPs, I will say, it's a concept that's really hard to understand for folks. Reid Robinson: Yeah, definitely don't think about the word. It really just is like app integrations for your AI tools. You can create these collections of tools from a...