User
Write something
AI Coffee hour with Zillion is happening in 4 days
Pinned
Welcome! READ THIS First 👀
I am so excited to share my passions for AI automation with you. I created this community for actual business owners that want to start implementing AI into their businesses to scale faster, with less staff. This community will NOT be free for long. I will be adding my automations piece-by-piece. These are the SAME automations I use in my Inc 5000 agency that enable us to scale to $700K/mo with few staff. Now some next steps... 1. INTRODUCE YOURSELF in the comments on this post. 2. ASK FOR HELP if you need it by posting in the 'Automation Help' category. Include loom videos. My team and the community will try to help. BEFORE asking for help, search for your issue in the search bar. 3. GIVE VALUE. Help others if they ask. Share your own automation templates and walkthroughs. 4. BLUEPRINTS are available inside the Classroom and separated by use case (Sales, content, etc). You may need to pay to unlock certain modules. 5. WAITING is available for our AI Automation Insider Ultra program. Details coming soon. Welcome to the AI Automation Insiders!
Welcome! READ THIS First 👀
Pinned
UPDATE: NEW AI AGENT MODULE LIVE 🔥
Hello NERDS! Hermes (Your AI Employee) is fully live in the classroom. It's the exact setup behind Bob, the agent I text all day on iMessage. In lesson one you watch me ask him to cancel a whole afternoon of team meetings for Labor Day. What's inside: - Why Bob runs on Hermes, and what an agent harness actually does - A server for about $5 a month, set up by Claude Code with my Hetzner VPS skill - Free iMessage for your agent, even if it lives on a VPS - Ads management, social scheduling, and replying to DMs and comments - Setting your agent up like a new hire, with its own GitHub, database and Gmail - Real threads from two weeks of messaging Bob (watch this one if you watch nothing else) -Use the Hermes desktop app and connect it to your VPS New Skills: - Claude Code will deploy your VPS, Remote in, and configure your ENTIRE agent - Improve, upgrade, configure your agent from your regular terminal - iMessage your agent 100% Free Premium members, start here: https://www.skool.com/ai-automation-insiders/classroom/4ac19b66?md=dd07c3c799694a358b79400510652fe8 Not premium yet? The module is in the paid tier. Upgrade here: https://leadgenjay.com/aia And if you'd rather skip setup entirely, we'll wake a pre-trained Hermes agent for you and you can iMessage it the same day: https://leadgenjay.com/hermes Which lesson are you starting with?
8
0
UPDATE: NEW AI AGENT MODULE LIVE 🔥
Pinned
🤖 Meet Bob, my Hermes agent.
Every Hermes tutorial out there ends the moment the agent turns on. Usually with a Hostinger link underneath. That's the easy part. Claude Code takes a Hetzner API token, picks the server, installs Hermes and connects itself over SSH. The one I spun up on camera costs about $6 a month. I never log into the dashboard. I type /bob in Claude Code when I need to fix or teach it. The rest of the time I text it on iMessage. The hard part is everything after, and that's what this video is. Bob gets his own Gmail, his own phone number, his own GitHub repo and his own Supabase back end, so everything he does carries his fingerprint and not mine. Composio wires him into the apps without me building a developer app for each one. Five Gmail accounts, Slack, calendar, all in one place. The tools nobody mentions: Unipile for Instagram and LinkedIn DMs older than 24 hours, about $5 an account. Photon for iMessage without owning a Mac mini. Doppler so your keys stop getting "rotated" by the model every time you paste one. And the nightly job: read the last 24 hours of your own work and rewrite your own instructions. Skills, tooling, rules. Get those three working together and you have an employee. Watch it here Do you have your own Bob?
GHL Affiliate
Hello Jay, is there still the possibility to register with you, in GHL and if so, which resources do I get? Thanks for your valuable content.
427 code-review loops with different models analyzed
One aspect of my current graph-engineering project morphisms is that every run is captured. I can define which model is used to write the code, and which one will review it. I often change models to see the impact it has over many runs and different tasks. The results are interesting and attached in images. What I learned: 1. Fable is NOT a good reviewer: it's not thorough 2. Gpt-5.6-sol and Astra are thorough and good reviewers - and also DON'T (!) favor their own work over other models (which is surprising, hats off to OpenAI) 3. Opus 5 sucks It's too early to say anything meaningful about deepseek v4.1 flash, though it's not looking great. Time will tell. It's cheap, fast, but I'm not yet confident in doing deep complex code-reviews in 100-200k token tasks. What I am now doing: 1. Use fable to write plans and write code if you can 2. Review the plan and code with gpt-models for thoroughness
1
0
427 code-review loops with different models analyzed
1-30 of 579
AI AUTOMATION INSIDERS
skool.com/ai-automation-insiders
Learn Claude Code, AI Agents, and N8N. Install the EXACT AI systems I use inside my $1mil/mo companies. Sell my systems as an AI Agency offer.
Leaderboard (30-day)
Powered by