I Built a New AI System in 3 Hours (and got paid $1650)

I Built a New AI System in 3 Hours (and got paid $1650)

by Nate Herk

Applied Sciences & Engineering AI — Models & Research UYQArtificial intelligence (AI)UYQFGenerative artificial intelligence
🎙 Nate Herk 👥 964K 📅 January 7, 2026 ⏱ 29 min 👁 28K 📄 tutorial 🧭 2026-08-28
Available in: English (current) Français

Keywords

AI workflown8nemail automationclient workfreelancing

Summary

The video documents the process of building an AI-powered email management system for a client, which was sold for $1650. The system consists of two main components: an inbox routing agent that classifies and logs incoming emails, and a personal email assistant accessible via Slack that can retrieve emails and draft responses in the client’s tone. The creator demonstrates the build live using n8n, showing how to set up Gmail tools, Google Contacts integration, and a subworkflow for email drafting with a custom writing style guide. He emphasizes the importance of system prompts for tone and behavior, and explains his approach to selling the workflow, including pricing and client communication. The video also includes reflections on what he would do differently and advice for beginners looking to start an AI automation business.

132 words

Critical Evaluation

Value of the Information & Strength of the Argument

The video provides substantial practical value for viewers interested in building AI workflows, especially with n8n. The step-by-step live build is clear and actionable, covering tool configuration, parameter handling, and subworkflow integration. The creator explains architectural decisions, such as using a subworkflow for email drafting to isolate the writing style, which demonstrates thoughtful design. The argumentation is based on personal experience and success, which is compelling but not scientifically rigorous. He does not provide evidence for the claimed $1650 payment beyond his own statement, and the video is essentially a tutorial rather than an objective analysis.

Scientific Rigor, Source Quality, Title Accuracy

The video does not cite external scientific sources; it relies on the creator’s expertise and practical demonstration. The tools used (n8n, Gmail, Google Contacts) are well-known, and the links in the description point to his courses and social media, which are promotional rather than authoritative. The title accurately reflects the content, and the video is well-structured with clear chapters. The creator’s claims about the effectiveness of his approach are not backed by empirical data, but the tutorial is internally consistent and technically sound.

194 words

Title / Content Match

The title accurately reflects the content: the creator builds an AI system in about 3 hours and discusses the $1650 payment. The video delivers on this promise.

Quality & Reliability

7/10

The video provides a detailed, practical walkthrough of building an AI workflow with n8n, including live demonstrations and architectural reasoning. The creator demonstrates competence but relies on anecdotal evidence and personal experience rather than formal validation. The claims about earning $1650 are plausible but unverifiable.

Chapters

Cited Sources

Concurring Sources

Contribution & Novelties

The video offers a practical, real-world example of building and selling an AI workflow, which is valuable for aspiring AI freelancers. It demonstrates a clear methodology for creating a personalized email assistant using n8n, including the use of subworkflows and style guides. The creator’s emphasis on system prompts for tone and behavior is a useful insight. However, the content is not novel in the AI field; it is a tutorial that applies existing tools and techniques.

Pour aller plus loin :

  • n8n documentation — Official documentation for n8n, the workflow automation tool used in the video.
  • Claude API documentation — Documentation for Claude models, which are used for the AI agents.
  • Prompt engineering guide — A comprehensive guide to prompt engineering, relevant to the system prompt design discussed.
  • Google Workspace APIs — Documentation for Gmail and Google Contacts APIs, which are integrated in the workflow.

145 words

Radar Profile

The radar profile shows high scores in quantity of information and technical level, reflecting the detailed tutorial nature. Quality of information is moderate, as it is based on personal experience rather than rigorous research. Overall reliability is lower due to lack of external validation.

Reliability 6/10

💬 Très positif. Sur les 30 commentaires analysés, la majorité exprime de l'appréciation et de l'inspiration, avec plusieurs demandes de contenu supplémentaire sur les aspects commerciaux et techniques.