This AI Workflow Replaces 10 Hours of Ad Research
Episode
31 min
Read time
2 min
Topics
Artificial Intelligence, Software Development, Product & Tech Trends
AI-Generated Summary
Key Takeaways
- ✓Automated trend scraping workflow: Build a system using Apify API to scrape TikTok by keyword and date range, pulling 20-200 videos with view counts, likes, and comments. Gemini then analyzes each video to extract visual hooks, product demonstrations, messaging themes, and funnel stage classification. This replaces manual scrolling and note-taking that previously consumed hours of researcher time.
- ✓Comment analysis for product insights: Configure Gemini to analyze video comments alongside content to identify common customer questions, complaints, and preferences about competitor products. This reveals gaps in market offerings and validates gut-skin connection beliefs or similar product hypotheses. The AI synthesizes patterns across thousands of comments that would take days to review manually.
- ✓Brand bible context system: Create a comprehensive brand profile including tone of voice, target audience definitions, customer pain points, and past campaign performance data. Feed this context to AI alongside trending video analysis to generate campaign briefs that match brand standards. The system produces 80 percent complete briefs requiring only human refinement before execution.
- ✓Creative brief automation pipeline: Connect trend research directly to brief generation by combining scraped video data, AI analysis, and brand context in one workflow. Output includes campaign names, objectives, target audience profiles, pain points, and key messaging. This compresses the research-to-strategy timeline from days to under 15 minutes for Facebook and TikTok ad campaigns.
- ✓Vibe coding over workflow builders: Start learning AI automation through Claude Code or Cursor rather than node-based tools like n8n or Make. Use AI to help build AI solutions by running Claude Code in one monitor and regular Claude for debugging in another. This approach proves more accessible for non-technical marketers than mastering API integrations and webhooks.
What It Covers
Mike Futia demonstrates how to automate TikTok ad research using AI workflows that scrape trending videos, analyze content with Gemini, and generate creative briefs in minutes. The system uses Apify for scraping, processes video transcripts and comments, and outputs campaign strategies based on viral content patterns for ecommerce brands and agencies.
Key Questions Answered
- •Automated trend scraping workflow: Build a system using Apify API to scrape TikTok by keyword and date range, pulling 20-200 videos with view counts, likes, and comments. Gemini then analyzes each video to extract visual hooks, product demonstrations, messaging themes, and funnel stage classification. This replaces manual scrolling and note-taking that previously consumed hours of researcher time.
- •Comment analysis for product insights: Configure Gemini to analyze video comments alongside content to identify common customer questions, complaints, and preferences about competitor products. This reveals gaps in market offerings and validates gut-skin connection beliefs or similar product hypotheses. The AI synthesizes patterns across thousands of comments that would take days to review manually.
- •Brand bible context system: Create a comprehensive brand profile including tone of voice, target audience definitions, customer pain points, and past campaign performance data. Feed this context to AI alongside trending video analysis to generate campaign briefs that match brand standards. The system produces 80 percent complete briefs requiring only human refinement before execution.
- •Creative brief automation pipeline: Connect trend research directly to brief generation by combining scraped video data, AI analysis, and brand context in one workflow. Output includes campaign names, objectives, target audience profiles, pain points, and key messaging. This compresses the research-to-strategy timeline from days to under 15 minutes for Facebook and TikTok ad campaigns.
- •Vibe coding over workflow builders: Start learning AI automation through Claude Code or Cursor rather than node-based tools like n8n or Make. Use AI to help build AI solutions by running Claude Code in one monitor and regular Claude for debugging in another. This approach proves more accessible for non-technical marketers than mastering API integrations and webhooks.
Notable Moment
Mike reveals he avoided n8n workflow automation for three to four months despite building AI tools, using simpler alternatives because he feared dealing with API keys and webhooks without coding background. He now recommends skipping n8n entirely and starting with vibe coding in Claude, which he considers easier for marketers to learn and more future-proof.
Episode Transcript
Hey, everyone. We are joined by Mike Futia today, and he is a amazing expert at Vibe Coding apps for marketing, and taking the pain out of your marketing, that redundant manual work that you have to do that you hate. He's gonna show you how to get rid of that, and we're gonna walk through a whole app he's built. We're gonna show you how to do better TikTok and Facebook ads. It's gonna be awesome. Let's get to today's show. Before we continue, let me tell you about a podcast I love, Marketing School. Marketing legends, Neil Patel and Eric Hsu, bring you daily actionable digital marketing lessons learned from years in the trenches. Marketing School delivers bite sized marketing wisdom you can implement immediately. Whether you have a new website or you're an established business, you'll learn the latest in SEO, content marketing, social media, email marketing, conversion optimization, and general online marketing strategies that work today. They just did a great episode called 10 SEO lessons that still work in the AI era. Listen to Marketing School wherever you get your podcasts. Mike, I'm very excited to have you on the show today. I first discovered you on Twitter because you'd built a really cool, like, Instagram trend research tool that I had found. And we were in the middle of HubSpot of kind of rebuilding how we do social and social organic and ads. And I was like, oh, this is awesome. Like, this is the kind of work that marketing has to do in this new modern post AI world. And so I was like, Let's get them on the show and, like, break it down and, you know, talk about that, but also just talk about, you know, the modern state of AI and building from marketing in general. But, you know, I think where we first connected was around so many marketers are doing manual trend spotting, manual research, and social still feels kinda clunky and old school, especially. And, like, you've been doing a bunch of work to kinda fix that. I'd love to hear how you've been doing that, like, what you've been building and everything there. Hey. Thanks a lot for having me on, Kip. I'm happy to get into this. And, yeah, the specific use case I think we're gonna talk about today, as you said, is scraping social media or searching social media for kind of trending topics in certain niches and, you know, having AI not only find that content for us, like going out and and scraping TikTok, for example, but also having AI analyze the videos. Right? As you know, Gemini now watch actual videos. So can we build a workflow or an internal tool or a system that teams can use where instead of, you know, having an employee literally go out on TikTok and kind of scroll the feed and find trending videos and take notes, can we automate some of that …
Get the full transcript (6,040 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.
You just read a 3-minute summary of a 28-minute episode.
Get Marketing Against the Grain summarized like this every Monday — plus up to 2 more podcasts, free.
Pick Your Podcasts — FreeKeep Reading
More from Marketing Against the Grain
The death of the CMO
Sep 8 · 34 min
The Productivity Show
What's Possible with AI in 2026: From Flashy Demos to Quiet Leverage (TPS600)
Feb 16
More from Marketing Against the Grain
Turn Every Comment Into a Lead - Automate DMs with Claude
Sep 3 · 38 min
How I AI
ChatGPT agent mode: The “little helper” that transformed recruiting, crafted user personas, and solved parking nightmares | Michal Peled (Honeybook)
Dec 8
Books, tools, and gear mentioned in this episode
SignalCast may earn commission on purchases via these links.
Tools
- GeminiRecommended
by Google
“Build a system using Apify API to scrape TikTok by keyword and date range, pulling 20-200 videos with view counts, likes, and comments. Gemini then analyzes each video to extract visual hooks, product demonstrations, messaging themes, and funnel stage classification.”
- Claude CodeRecommended
by Anthropic
“Start learning AI automation through Claude Code or Cursor rather than node-based tools like n8n or Make.”
“Mike reveals he avoided n8n workflow automation for three to four months despite building AI tools, using simpler alternatives because he feared dealing with API keys and webhooks without coding background. He now recommends skipping n8n entirely and starting with vibe coding in Claude.”
- CursorRecommended
“Start learning AI automation through Claude Code or Cursor rather than node-based tools like n8n or Make.”
“Start learning AI automation through Claude Code or Cursor rather than node-based tools like n8n or Make.”
- ApifyRecommended
by Apify
“The system uses Apify for scraping, processes video transcripts and comments, and outputs campaign strategies based on viral content patterns for ecommerce brands and agencies.”
- ClaudeRecommended
by Anthropic
“Start learning AI automation through Claude Code or Cursor rather than node-based tools like n8n or Make. Use AI to help build AI solutions by running Claude Code in one monitor and regular Claude for debugging in another.”
podcast
“SPONSORS: Marketing School podcast”
More from Marketing Against the Grain
We summarize every new episode. Want them in your inbox?
The death of the CMO
Turn Every Comment Into a Lead - Automate DMs with Claude
Using Codex to build a Research Dashboard/System
Claude vs. Human Marketer: Which Is Actually Better?
How to Stop AI from Killing Your Critical Thinking w/ David Epstein
Similar Episodes
Related episodes from other podcasts
The Productivity Show
Feb 16
What's Possible with AI in 2026: From Flashy Demos to Quiet Leverage (TPS600)
How I AI
Dec 8
ChatGPT agent mode: The “little helper” that transformed recruiting, crafted user personas, and solved parking nightmares | Michal Peled (Honeybook)
My First Million
Oct 21
5 AI Tools I’d Use to Make $1M (w/o employees, capital, or time)
How I AI
Aug 10
Claude Code for normal people: skills, voice mode, and how to collaborate with AI
How I AI
Jul 13
This solo builder runs 24/7 local AI on his own hardware | Alex Finn
Explore Related Topics
This podcast is featured in Best Marketing Podcasts (2026) — ranked and reviewed with AI summaries.
Read this week's AI & Machine Learning 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 DigestNo credit card · Unsubscribe anytime