Skip to main content
Marketing Against the Grain

I Used ChatGPT & n8n to Stop Customers from Leaving | Tina Huang

29 min episode · 2 min read
·
Tina Huang

Episode

29 min

Read time

2 min

Topics

Investing, Fundraising & VC, Artificial Intelligence

AI-Generated Summary

Key Takeaways

  • AI Workflow Fundamentals: Map repetitive tasks by recording screen shares of recurring work blocks, then upload to Gemini to analyze what can be automated and calculate time savings across your week.
  • Agent Building Components: Every functional AI agent requires six core elements—large language model, tools, knowledge and memory systems, audio capabilities, guardrails, and evaluation frameworks—similar to essential burger ingredients that can be customized.
  • Domain Expertise Over Technical Skills: The most valuable agentic systems come from people with deep domain knowledge in fields like pest control or pharmaceuticals, not engineers, because they understand workflows and can properly evaluate agent performance.
  • Evaluation Framework Priority: Start with five evaluation tests minimum to measure agent output consistency against expected results, then iteratively improve prompts based on failure rates rather than guessing at improvements without quantifiable metrics.

What It Covers

Data scientist Tina Huang demonstrates how domain experts can build AI workflows to solve business problems like customer churn, using tools like ChatGPT and n8n without extensive coding knowledge.

Key Questions Answered

  • AI Workflow Fundamentals: Map repetitive tasks by recording screen shares of recurring work blocks, then upload to Gemini to analyze what can be automated and calculate time savings across your week.
  • Agent Building Components: Every functional AI agent requires six core elements—large language model, tools, knowledge and memory systems, audio capabilities, guardrails, and evaluation frameworks—similar to essential burger ingredients that can be customized.
  • Domain Expertise Over Technical Skills: The most valuable agentic systems come from people with deep domain knowledge in fields like pest control or pharmaceuticals, not engineers, because they understand workflows and can properly evaluate agent performance.
  • Evaluation Framework Priority: Start with five evaluation tests minimum to measure agent output consistency against expected results, then iteratively improve prompts based on failure rates rather than guessing at improvements without quantifiable metrics.

Notable Moment

Huang reveals that building functional business AI workflows requires only four to six hours weekly over twenty eight days to gain baseline proficiency, making advanced automation accessible to non-technical domain experts.

Know someone who'd find this useful?

Episode Transcript

Hey, everyone. I just had a great conversation with Tina Wong. She is a data scientist turned creator and builder and she is awesome at building agents. And we just had the most positive insight which is the next generation of builders over this next year are gonna be the best marketers, the best sales people, the best business people. They're not gonna be the best technical people. And so what we did is we built an episode for all of you to show you how you can take your domain deep knowledge and build awesome AI workflows to actually solve your problems and scale the knowledge that you have. This is gonna be a great show. Let's get into today's episode. Did you know that most businesses only use 20% of their data? That's like reading a book with most of the pages torn out or paying for a coffee that's one fifth full. Point is, you miss a lot unless you use HubSpot. Their customer platform gives you access to the data you need to grow your business. The insights trapped inside emails, call logs, and transcripts, all that unstructured data that makes all the difference. Because when you know more, you grow more. More. Visit hubspot.com today. So, Tina, thank you for being on the show today. We're excited to have you. Thank you so much for having me. You have very interesting background. You are deep into data. You're a former data scientist. But now you're a creator, You're an entrepreneur, and you teach the world how to build amazing AI workflows, and you work with companies to build amazing AI workflows. So I guess I wanna start with what is the state of the work you can do with AI today? Tell me, like, the most popular workflows that you are teaching people, building for people. Give us kinda the background lay of the land. Yeah. For sure. For sure. So the most useful workflows are usually not the coolest workflows. So True. That is very true. It's like, what's the coolest kind of workflow? You know, we can make all these robots. What's the most useful workflow? We can make reports. Exactly. Right? Yeah. So I would say there's a lot of report workflows that we work on. These are very custom because Mhmm. Companies generally have a very specific way of doing their reports, and a lot of companies have to do a lot of reports to their investors, to their stakeholders, you know, a lot of different types of people. So that's a very popular workflow that people try to automate with agent tech AI. Another one is customer service. Mhmm. Customer service, like email list, these kind of things. So, for example, we will have people, who would be sending emails, and they'd be able to respond to those emails in a more personalized way. That's also a very common and useful workflow because the majority of questions that people say …

Get the full transcript (5,503 words) + summary by email — free

One-time email with the complete transcript and AI summary of this episode. No account needed.

One email, no spam. We’ll also show you what SignalCast does.

Browse all Marketing Against the Grain transcripts →

You just read a 3-minute summary of a 26-minute episode.

Get Marketing Against the Grain summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

Books, tools, and gear mentioned in this episode

SignalCast may earn commission on purchases via these links.

Tools

  • by OpenAI

    Data scientist Tina Huang demonstrates how domain experts can build AI workflows to solve business problems like customer churn, using tools like ChatGPT and n8n without extensive coding knowledge.
  • Data scientist Tina Huang demonstrates how domain experts can build AI workflows to solve business problems like customer churn, using tools like ChatGPT and n8n without extensive coding knowledge.
  • by Google

    Map repetitive tasks by recording screen shares of recurring work blocks, then upload to Gemini to analyze what can be automated and calculate time savings across your week.

company

  • 💼 SPONSORS [HubSpot]

More from Marketing Against the Grain

We summarize every new episode. Want them in your inbox?

Similar Episodes

Related episodes from other podcasts

Explore Related Topics

This podcast is featured in Best Marketing Podcasts (2026) — ranked and reviewed with AI summaries.

Read this week's Investing & Markets Podcast Insights — cross-podcast analysis updated weekly.

You're clearly into Marketing Against the Grain.

Every Monday, we deliver AI summaries of the latest episodes from Marketing Against the Grain and 192+ other podcasts. Free for one show.

Start My Monday Digest

No credit card · Unsubscribe anytime