More How I AI episodes

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

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

Published 2 Feb 2026

Duration: 00:40:28

The podcast explores how Model Connector Platforms (MCPs) enable automation of tasks by connecting AI assistants with external systems and SaaS applications.

Episode Description

Reid Robinson, Principal AI Product Strategist at Zapier, shares how he uses Model Context Protocols (MCPs) to automate tedious tasks and create power...

Overview

The podcast focuses on Model Connector Platforms (MCPs), which function as integration tools that enable AI assistants to communicate with external systems and perform automated tasks. These platforms, such as Zapier, allow AI tools like Claude to interact with a variety of SaaS applications, streamlining processes like CRM updates, meeting note generation, and daily planning. The conversation emphasizes the significance of enterprise-level integration, particularly the necessity of security and compliance measures when linking AI with internal systems.

Additionally, the episode touches on the complexity of MCPs and the need for more user-friendly interfaces to simplify their use. It also discusses the advantages of organizing AI workflows with specific instructions and project structures to enhance efficiency. Beyond professional applications, the podcast explores how AI can be used personally, for example, in creating family calendars, generating music, and preparing for job interviews. The discussion concludes with reflections on the future of AI tool design and the growing role of automation in boosting productivity across both personal and professional domains.

Recent Episodes of How I AI

4 May 2026 The internal AI tool thats transforming how Stripe designs products | Owen Williams

Existing design tools like Figma struggle with creating realistic, interactive data dashboards, but the internal tool protodash automates 90% of dashboard construction using React and cursor rules, integrates with design systems, and enables immersive prototypes that enhance design reviews, user testing, and iterative development through real data, dynamic components, and AI-assisted coding.

22 Apr 2026 What Claude Design is actually good for (and why Figma isnt dead, yet)

Emerging AI tools like Claude Design leverage structured design systems for prototyping and interface generation, offering brand-consistent outputs but facing challenges like font discrepancies and reliance on user input, alongside potential to complement or replace platforms like Figma in specific workflows.

More How I AI episodes