Nate Herk Built an n8n Agent That Finds Viral YouTube Patterns and Earns Him $6K Per Month
A no-code n8n workflow that scans any YouTube niche for viral outliers, extracts what makes top videos work, and surfaces daily content ideas from audience comments — which Nate now sells as a productized service.
Continue exploring this workflow
The Strategy
Nate Herkelman is a former Goldman Sachs business intelligence analyst who left corporate in November 2024 to build an AI automation agency. One of the first things he built and documented publicly is a YouTube content strategy agent that runs entirely in n8n — no code required. The problem it solves is one most creators face: knowing which content directions are actually working in your niche right now. Most YouTubers either study competitors manually (slow and inconsistent) or skip competitive research entirely. Nate's agent automates the discovery loop. The system runs on two schedules. Weekly, it scans for viral outliers in a target niche by analyzing channels for videos that significantly outperformed their typical view counts. The agent extracts what made those videos work: title structures, topic angles, thumbnail patterns, and recurring hooks. Daily, it monitors comments on high-performing videos to surface questions, frustrations, and content requests straight from the audience. These signals feed into a content pipeline the creator can review and act on each week. Nate sells this as a done-for-you productized service to other creators and automation buyers, and makes the n8n template freely available on his YouTube channel. He reports $6,000 per month from the service.
How It Works
Configure the n8n workflow with your niche by providing 3 to 5 competitor or reference channel IDs.
Weekly trigger: the agent queries the YouTube Data API for each channel's recent videos and calculates each video's view-to-subscriber ratio to identify statistical outliers that overperformed.
For each viral outlier found, the agent pulls the title, description, and top comments, then sends these to an AI model (Claude or GPT) to extract patterns across all overperforming videos.
The AI outputs a structured analysis: which title formulas are working, which topics are spiking, and what audience questions are being answered in the comments.
Daily trigger: the agent monitors comments on the top-performing videos in the niche, clustering recurring questions and viewer requests that could become standalone video topics.
All outputs feed into a connected spreadsheet or Notion database, building a running library of researched, data-backed content opportunities.
Nate packages the configured workflow and the weekly strategy reports it generates into a monthly retainer service for creators who do not want to run n8n themselves.
Results
Nate Herk reports $6,000 per month from selling this YouTube strategist agent as a productized service. These figures are self-reported in his YouTube video and course materials. The free n8n workflow template is publicly available for builders who want to replicate or adapt the system. YouTube Data API access is free within standard quota limits, keeping the data acquisition cost at zero.
Our Take
The insight here is about packaging rather than just building. A lot of automation builders create useful n8n workflows and give them away or treat them as lead magnets. Nate recognized that a creator who does not want to touch n8n will pay for a packaged service that tells them what to make next — not just for the data, but for the removed decision-making friction. The YouTube Data API is generous at the free tier (10,000 units per day), which makes the data layer essentially free to run. The AI analysis cost for weekly scans is minimal. The margin is in the interpretation and delivery. The architecture transfers cleanly to other content platforms. The same pattern — find outliers, analyze what worked, surface audience questions — applies to podcasts, newsletters, LinkedIn posts, or any platform with enough public performance data. The specific tool calls change; the logic does not.
Frequently Asked Questions
The practical questions a builder or operator is likely to ask before trying a strategy like this.
What does this agency AI agent actually do?
This agency AI agent is a real workflow where the agent takes on an operational job, not just a brainstorming task. Nate Herk Built an n8n Agent That Finds Viral YouTube Patterns and Earns Him $6K Per Month shows what that looks like in practice. A no-code n8n workflow that scans any YouTube niche for viral outliers, extracts what makes top videos work, and surfaces daily content ideas from audience comments — which Nate now sells as a productized service. The practical value comes from the agent handling repeatable business work with enough autonomy that a human only steps in after context has already been gathered.
Who should use a agency AI agent like this?
This example is most relevant for agency operators. It is especially relevant for businesses where speed to lead, after-hours coverage, or consistent intake quality directly affects revenue. The category here is Content Creation, which means the best fit is a team looking to turn a manual bottleneck into a repeatable system with a agency AI agent.
Which tools are used in this agency AI agent setup?
The source names n8n, OpenAI, YouTube. That matters because one of the strongest signals in this directory is whether the operator shared the actual stack. Named tools make a agency AI agent strategy far more useful than vague claims about “an AI system” doing the work.
How hard is it to implement a agency AI agent like this?
Intermediate difficulty is the current read. The listing suggests a launch window of days. Startup cost is listed as $50-200/mo. We were able to extract 7 concrete workflow steps from the source. We would treat a agency AI agent like this as a workflow that needs real business context, testing, and exception handling rather than something you should copy blindly from one prompt.
What results can a agency AI agent produce?
Nate Herk reports $6,000 per month from selling this YouTube strategist agent as a productized service. These figures are self-reported in his YouTube video and course materials. The free n8n workflow template is publicly available for builders who want to replicate or adapt the system. YouTube Data API access is free within standard quota limits, keeping the data acquisition cost at zero.
How credible is this agency AI agent case study?
Right now the evidence comes from a YouTube video. That is enough for us to study and curate the workflow, but not enough on its own to treat this agency AI agent like an audited case study. We look for named tools, concrete results, and enough workflow detail to understand what was actually deployed, then we add our own editorial judgment on top.
Related Strategies
More AI agent strategies you might find useful
52 AI Generated YouTube Videos in 6 Weeks With 30,000 Views and Zero Manual Editing
An autonomous AI pipeline published 52 YouTube videos in 6 weeks, generating 30,…
Nate Herk Built an AI Voice Agent That Calls Every New Lead Within Seconds of Their Form Submission
An n8n + Vapi workflow that triggers an outbound AI phone call the moment a lead…
David Johnson-Igra Lost All His Ghostwriting Clients to AI in 2025 — Then Rebuilt His Business Selling AI-Powered Executive Voice Systems
A tech ghostwriter who worked with Amazon, a16z, Meta, GitHub, and OpenAI watche…
A Thoracic Surgeon Handed His YouTube Channel to Two AI Agents for Six Weeks. Here Is What Actually Happened.
Wei-Ciao Wu built two Claude agents — Midnight for production and Dusk for promo…
Want more strategies like this?
Get weekly AI agent case studies in your inbox.