Jan 26, 2026 · 34m · mixergy
#2295 Ryan Carson: How AI does my marketing for me
0:00 / 0:00
gold bands on the timeline = statements, start to end. Hover to read, click to jump. CC turns on captions
Serial entrepreneur Ryan Carson joins Andrew Warner to explain how he leverages autonomous AI agents, structured telemetry, and custom automated pipelines to execute hyper-personalized marketing and rapid software development for his startup, Untangle.
How this conversation actually went
Every chapter scored 0–10 on four independent dynamics. Hover any point for the reasoning behind the score. Andrew holds 20.1% of the talking time here. How this is scored →
Andrew as informed peer 4.5 Guest teaching 4.0 Guest disagreement 0.7 Andrew pushing back 2.2
speaking balance: gold is Andrew, purple is the guest (3 minute bins)
Sharpest disagreement ▶ 29:25 Ryan dismisses over-engineering customer enrichment
Ryan rejects the premise that founders need complex third-party external data scraping, asserting that basic contextualization and custom LLM copy beat conventional practices.
Hardest push from Andrew ▶ 22:58 Andrew questions the coding hype over marketing fundamentalsAndrew pushes back against the developer obsession with viral coding loops, pointing out that customer acquisition and distribution are being ignored.
Biggest teaching moment ▶ 9:31 Infinite lead nurturing loop architectureRyan educates the audience and host on structuring infinite, monthly LLM-driven nurture loops that automatically reference a proprietary content library rather than exhausting human copywriters.
Andrew holds their own ▶ 14:41 Andrew explains Zapier's evolving AI orchestrationAndrew demonstrates deep practical expertise by detailing a multi-app Claude-to-Grain workflow and explaining why Zapier's new native AI model solves friction.
the scores for every segment, with the reasoning behind each
| Chapter | Topic | Andrew as informed peer | Guest teaching | Guest disagreement | Andrew pushing back | Why |
|---|---|---|---|---|---|---|
| Reimagining Drip Campaigns with AI Personalization | 4 | 4 | 1 | 2 | Andrew opens by probing why Ryan didn't simply use existing email service providers, prompting Ryan to explain the shift from static templates to bespoke, AI-generated drips. Andrew quickly grasps the mechanics and synthesizes specific user persona scenarios for Untangle. | |
| Step-by-Step Architecture of an AI Email Drip Pipeline | 4 | 5 | 0 | 2 | Ryan presents a screen share breaking down his step-by-step pipeline from lead magnet capture to hourly cron jobs and LLM prompts. Andrew asks targeted clarifying questions regarding tool choices like Resend and the trade-offs of tracking clicks over open rates. | |
| Vertical AI Agents and Workflow Orchestration with Zapier | 6 | 3 | 0 | 3 | When Zapier is brought up, Andrew takes the lead by detailing his firsthand workflow frustrations and how Zapier functions as an AI orchestrator rather than just a legacy webhook bridge. Ryan enthusiastically concurs with Andrew's assessment of modern automation workflows. | |
| Multi-Agent Software Development via AMP and Ghostty | 3 | 5 | 1 | 1 | Ryan demonstrates running multiple parallel terminal sessions of AMP within Ghostty to build software features simultaneously. Andrew observes the CLI workflow and asks about the operational efficiency of multi-agent development. | |
| Bridging the Gap Between Rapid Coding and Marketing Execution | 5 | 4 | 1 | 3 | Andrew challenges the tech industry's hyperfocus on code generation over actual customer acquisition and go-to-market execution. Ryan agrees, elaborating on his daily midnight cron job that prompts Claude to act as an automated VP of Marketing. | |
| Practical Marketing Cadence and Emerging SaaS Opportunities | 5 | 3 | 1 | 2 | Andrew presses Ryan on whether the daily AI recommendations surpass experienced human marketing intuition, citing Ryan's early DropSend marketing background. Andrew wraps up by pitching an independent SaaS idea for personalized multi-list AI drip platforms. |
Statements from this episode (10)
Carson: Untangle runs daily Claude Opus cron jobs for marketing recommendations
“Every day I have a cron job that basically looks at key marketing stats, and then it passes those stats to Opus four or five, and then it generates an email with recommendations on what is the one thing I should do to improve my marketing funnel today.”
Carson: Resend won by mastering Answer Engine Optimization for AI agents
“You know, what's funny is I think they crushed it on AEO answer engine optimization. Because when I was talking to AMP about this, you know, like, hey, I want to send emails, you know, programmatically, it was like, why not resend?”
Carson: Modern email marketers avoid tracking opens to protect sender reputation
“What's common today is often not to use open because it'll degrade your sending score. So we just use click and bounce.”
Untangle's AI divorce agent uses state statutes to write AEO content
“So for Untangle, we have Grace. She's our AI divorce agent. She's inside of Untangle. Now, she has specific tools, right? They're very specific to our vertical, right? You know, divorce statute search, case law search, child support guideline search, right? Th…”
Carson: The same vertical AI agent should write company content and emails
“You're going to have an agent that has specific skills. That should be the agent that writes your content. That should be the agent that writes your emails. Like this is all the same entity.”
Carson: AMP's deep mode uses GPT-5.2 instead of Opus 4.5
“I'm actually secretly showing you a new feature. If you see deep here this is a mode. We're actually using a GPT five, two instead of Opus four or five.”
Carson: I run three AMP coding agents simultaneously
“Now, what I actually do is I actually run three of these agents at a time. So I actually have three amps open any one time, and I'm usually working on three different parts of the app at once.”
Carson: AMP will autonomously implement marketing optimizations as pull requests
“I'm thinking the next step is, is not just to get the email, but actually have AMP implement the suggestion. And then I wake up to a PR that I review where it's actually done the thing that it suggested, and then I get to review that instead.”
Carson: AI Marketing Agent Replaces a $250k VP of Marketing
“I think these are all insights that a human being would have had, but I would have had to pay a VP of marketing, you know, 250,000 dollars a year to have that insight.”
Carson: AI Agents Need Domain Context Rather Than Heavy Data Enrichment
“Connecticut specific documents in Markdown, right? That are fed, you know, into the agent as a tool. So You got to give your agent the right tools in the right context. But I don't think you need to do as much like external enrichment as people think.”