How Zapier’s EA built an army of AI interns to automate meeting prep, strengthen team culture, and scale internal alignment | Cortney Hickey
Episode
44 min
Read time
2 min
Topics
Remote Work, Relationships, Leadership
AI-Generated Summary
Key Takeaways
- ✓Weekly Meeting Prep Agent: Automated Friday workflow researches external meeting participants via web search, checks CRM relationships in HubSpot, scans Gmail and Slack history, then creates Todoist tasks two hours before meetings and delivers structured Slack digest with prep recommendations.
- ✓Automated Meeting Feedback System: Post-meeting agent analyzes transcripts against company values and Five Dysfunctions of a Team framework, sends direct Slack feedback to all participants highlighting one to two growth opportunities, normalizing continuous feedback without ego threat from human managers.
- ✓Executive Prep GPT: Custom ChatGPT trained on company strategy memos, team norms, and past feedback helps employees stress-test documents before executive review, resulting in 278 users sharpening strategy docs, reducing meeting bottlenecks, and sometimes eliminating meetings entirely when clarity is achieved.
- ✓Strategy Companion in NotebookLM: Knowledge base containing dozens of sources including strategy documents, all-hands transcripts, and org action plans allows employees to query how their role connects to company strategy, with auto-generated podcast summaries making strategy interactive rather than static.
What It Covers
Cortney Hickey, EA to Zapier's CEO, demonstrates how she built AI agents to automate meeting preparation, enforce company cultural values through automated feedback, and scale strategic alignment across the organization.
Key Questions Answered
- •Weekly Meeting Prep Agent: Automated Friday workflow researches external meeting participants via web search, checks CRM relationships in HubSpot, scans Gmail and Slack history, then creates Todoist tasks two hours before meetings and delivers structured Slack digest with prep recommendations.
- •Automated Meeting Feedback System: Post-meeting agent analyzes transcripts against company values and Five Dysfunctions of a Team framework, sends direct Slack feedback to all participants highlighting one to two growth opportunities, normalizing continuous feedback without ego threat from human managers.
- •Executive Prep GPT: Custom ChatGPT trained on company strategy memos, team norms, and past feedback helps employees stress-test documents before executive review, resulting in 278 users sharpening strategy docs, reducing meeting bottlenecks, and sometimes eliminating meetings entirely when clarity is achieved.
- •Strategy Companion in NotebookLM: Knowledge base containing dozens of sources including strategy documents, all-hands transcripts, and org action plans allows employees to query how their role connects to company strategy, with auto-generated podcast summaries making strategy interactive rather than static.
Notable Moment
The CEO requested tougher automated feedback after initial versions were too soft, leading to AI-generated coaching that directly calls out issues like fear of conflict and slow decision-making, which employees accept more readily than human criticism.
You just read a 3-minute summary of a 41-minute episode.
Get How I AI summarized like this every Monday — plus up to 2 more podcasts, free.
Pick Your Podcasts — FreeKeep Reading
More from How I AI
Claude Opus 5 review: this model is brilliant (but annoying)
Jul 24 · 24 min
SaaStr Podcast
SaaStr 845: How SaaStr Built a $5 million Pipeline Machine with 1.5 Humans and 20 AI Agents with SaaStr's Chief AI Officer and Momentum from Salesforce's VP of GTM
Mar 11
More from How I AI
Computer & browser use in Codex (5 real examples)
Jul 22 · 27 min
The Productivity Show
What's Possible with AI in 2026: From Flashy Demos to Quiet Leverage (TPS600)
Feb 16
Books, tools, and gear mentioned in this episode
SignalCast may earn commission on purchases via these links. As an Amazon Associate, SignalCast earns from qualifying purchases.
Books

“Post-meeting agent analyzes transcripts against company values and Five Dysfunctions of a Team framework”
Tools
“Strategy Companion in NotebookLM: Knowledge base containing dozens of sources including strategy documents”
“creates Todoist tasks two hours before meetings”
“checks CRM relationships in HubSpot”
“Custom ChatGPT trained on company strategy memos, team norms, and past feedback”
More from How I AI
We summarize every new episode. Want them in your inbox?
Claude Opus 5 review: this model is brilliant (but annoying)
Computer & browser use in Codex (5 real examples)
How the founder of Morning Brew built a Claude content machine that never runs out of ideas and never sounds like slop | Alex Lieberman
This solo builder runs 24/7 local AI on his own hardware | Alex Finn
GPT-5.6 Sol vs. Claude Fable: Why OpenAI’s new model crushes my benchmark
Similar Episodes
Related episodes from other podcasts
SaaStr Podcast
Mar 11
SaaStr 845: How SaaStr Built a $5 million Pipeline Machine with 1.5 Humans and 20 AI Agents with SaaStr's Chief AI Officer and Momentum from Salesforce's VP of GTM
The Productivity Show
Feb 16
What's Possible with AI in 2026: From Flashy Demos to Quiet Leverage (TPS600)
Marketing Against the Grain
Feb 5
This AI Workflow Turns Every Sales Call Into a Custom Deck
SaaStr Podcast
Feb 4
SaaStr 840: From 1 Agent to 20+: The Reality of Managing Multiple AI Agents Across Your GTM with SaaStr's CEO and CAIO
Hard Fork
Feb 4
Moltbook Mania Explained
Explore Related Topics
This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.
You're clearly into How I AI.
Every Monday, we deliver AI summaries of the latest episodes from How I AI and 192+ other podcasts. Free for one show.
Start My Monday DigestNo credit card · Unsubscribe anytime