Ryan Carson uses AI to customize email drip

About this episode

Presented by Zapier
https://zapier.com/

Episode Highlights / Timestamps

00:00 Why every email should be personalized
00:18 Ryan’s background and what Untangle does
00:45 Rethinking traditional email drips
01:12 Customizing emails based on user situations
01:39 A real example that led to a signup
02:06 Daily automated marketing insights via email
03:00 Doing things that don’t scale with AI
04:03 Walking through the AI email system
05:06 Using lead magnets and contextual data
06:09 Enriching leads and storing user context
06:45 Hourly cron jobs and email scheduling
07:39 Feeding context into the LLM correctly
08:15 Preventing hallucinated features
08:24 Sending emails with Resend
09:18 Measuring clicks instead of opens
10:12 Layering engagement-based follow-ups
10:39 Long-term personalized nurture loops
12:00 Turning marketing emails into real value
13:03 Building vertical-specific AI agents
14:15 Using Zapier and modern automations
16:12 Building systems with AI coding agents
18:27 Running multiple AI agents at once
21:27 Deciding what to build in a world of “free code”
24:09 Daily AI-generated growth recommendations
27:45 Using AI to generate and validate ideas
31:03 Increasing insight frequency, not brilliance
34:21 Why personalized email is a massive opportunity
34:48 Final takeaways

Why isn’t every email completely customized for the person receiving it — especially now that AI can do it for us?

In this episode of The Next New Thing, Andrew Warner sits down with Ryan Carson, a three-time founder currently building Untangle, to walk through a very practical, very real AI system he uses every day to grow his business.

Ryan has spent over 25 years building startups, but while setting up a “standard” email drip for Untangle, he stopped and asked a simple question: why are we still sending the same emails to completely different people? Instead of writing dozens of templates, he built an AI-powered workflow that generates fully personalized emails — based on each user’s situation, behavior, and engagement — and adapts over time.