Hi all, I’ve been struggling with applying Alex Hormozi’s frameworks in a practical way. Every time I read $100M Offers or $100M Leads, I’d get inspired… but then forget the exact quote or framework when I needed it most. I know a lot of people here have felt the same. So last week I built something to fix that: a RAG chatbot trained on Hormozi’s books. Now I can just ask: • “Give me 3 ways to increase perceived value in my offer” • “What’s Hormozi’s take on pricing guarantees?” • “Summarize how to get attention for my business” And it answers instantly, with exact references from the books. Here’s how I set it up: 1. Scraped + cleaned the books into Markdown (so the data is structured). 2. Used a vector database (Supabase) to store the chunks. 3. Plugged it into a simple RAG flow in n8n with OpenAI for the responses. 4. Wrapped it in a lightweight chat UI built with NextJS so it feels like ChatGPT—but with Hormozi’s brain on tap. If anything is unclear, let me know. Hope this helps you if you also want an “Hormozi GPT” for when you’re working on your business.

Whipped this up today and it's already saved me hours processing 1000+ resumes! It's an AI technical recruiter in n8n (selfhosted, local) to help me screen initial resumes. The purpose is to quickly respond to candidates who are a potentially good fit and screen out resumes that don't fit the role at all (e.g. all Java, no Typescript). It has 3 triggers: - new applicant via job board, which sends me an email with resume attached - new applicant via linkedin, which directs candidates to google form, then resume gets dropped into google drive - manual trigger to bulk process lots of past applicants in my gmail (label: Hiring) Then upload resume to ChatGPT. I make a custom API call to OpenAI RESPONSES endpoint and pass in the file id, so that ChatGPT can analyze the resume and extract the candidate's email address. Finally, ChatGPT returns json with explanation of its decision. You could also return a confidence score, then adjust the threshold. The last step is to send a follow up email to candidate with next steps. Here's the simple ChatGPT prompt - I removed a bunch of scoring criteria, but you'd put them in the "general guidelines" section. GPT 4.1 is probably overkill for this task and you do get niceties like structured JSON output if you stick with 4o family: ``` { "model": "gpt-4.1", "temperature": 0, "input": [ { "role": "user", "content": [ { "type": "input_text", "text": "You are a technical AI recruiting assistant. Analyze the attached resume and decide whether to proceed with an interview for a senior backend engineer with 5+ years of Typescript. Also extract the candidate's email from the resume. General guidelines: 1 2 3 4 5 6. You are welcome to make exceptions to these guidelines if you believe the candidate is exceptionally talented. Return JSON like {\"should_proceed\": false, \"explanation\": \"2 sentence explanation of decision\", \"email_address\": \"[email protected]\"}." }, { "type": "input_file",

Yesterday we wrapped up filming the first ever Agentic Arena in NYC. An AI agent building competition between me and the legendary Jack Roberts… It will premiere on YouTube on September 5th at 3pm EST, make sure to tune in!! We’ll have to see if I was able to bring it home for the AIS family!! 😬 Cheers, Nate

Let's get to know each other! Comment below sharing where you are in the world, a career goal you have, and something you like to do for fun. 😊

Read this article and it's a brilliant reminder of why I've turned to n8n opportunities. "We Put Agentic AI Browsers to the Test - They Clicked, They Paid, They Failed" https://guard.io/labs/scamlexity-we-put-agentic-ai-browsers-to-the-test-they-clicked-they-paid-they-failed This is why I’ve been hesitant to jump on the “Agentic AI” bandwagon. How are you approaching this? It looks magical but prompt injection scares me. Malicious sites can hide instructions in the page itself, steering the AI to act in ways you never intended. There’s a clear distinction in risk and upside: - Chat-based agents (ChatGPT, Claude) are bounded. They run inside the app, call APIs, fetch info. Even with browsing they’re limited, usually read-only, not fully autonomous. - Browser agents (Comet, AutoGPT) are autonomous. They browse, click, fill forms, even buy things for you. That’s where the danger multiplies. Tactics I’m considering in testing to stay safe: - Run browser agents in a separate profile (dummy payment details, non-critical accounts) - Use for research, not execution (compare prices, scrape details, draft summaries) - Add boundary prompts: Never submit forms. Never purchase. Pause at checkout The upside is obvious with hands-free workflows, scaled attention. But until guardrails mature, I’ve held back. Hiring an eager intern with superpowers only works if you: - Contain them - Give clear rules - Review before letting them act Until then, I’m doubling down on n8n workflows to automate daily tasks safely, & on my terms.