I spent 100 hours testing Claude Code vs ChatGPT Codex and what I found genuinely surprised me. Same prompts, same builds, both tools side by side, and one of them hit way harder than I expected. If you're picking between coding agents right now, then this video is the breakdown you actually need before you commit.

If you're building AI agents, I'd urge you to create a template for prompting. Two notable builds in the last month as proof: - I've built an AI agent that has handled over 9,000 emails - Another AI agent that's handling 25k customers. But here's the full setup: - A claude.md file that references a prompting guideline file, it tells Claude how to write prompts. - Once a prompt is approved, I write at the top "approved for production" which tells Claude that it should not make big changes. This makes sure that the prompt does not get destroyed by Claude. - Push the changes to my GitHub to keep track of all changes. This last part is where most people go wrong. When they see a mistake, they ask Claude to write an explicit rule to never do that again. The issue is that Claude will only look for that exact case, and if the next case doesn't match it, Claude will skip it. Instead, what I do is write mental models of the idea, what we're trying to do and why. When you do it this way, Claude has to use more reasoning to figure out which mental model makes sense. You're letting Claude think with some constraints. But this system has cut down my prompting time and also increased my reliability ten fold. And the thing is that I can use this wherever AI agents are used. Sales agent, customer service agent, any type of agent. Because the structure is the exact same every single time. Give me the agent and I'll make it reliable.

When fellow members @David O'Donnell and @Brooks M shared information in this community about the “AI-Assisted Zero-Day 2FA Bypass Now in the Wild,” it prompted me to take a much closer look at my own security posture. I paused my planned work to conduct a security audit across my own architecture and ecosystem, and I am very glad I did. The process showed me that cybersecurity risks are far more complex, sophisticated, and easy to underestimate than many of us may realise. Like many developers, I had relied on standard operating system protections, VPNs, and a mix of paid or free security tools. A deeper review revealed multiple potential vulnerabilities and a much broader threat surface than I expected. I have since implemented emergency defensive hardening across 26 mechanisms and 9 distinct threat-category areas, including incident-response readiness. I have also attached my “Defensive Hardening for AI Developers” report for anyone who may find it useful. I am sharing this because I genuinely do not want any member here to become a cybersecurity victim. Please consider reviewing your own systems, especially if you handle client data, where the legal, financial, and reputational stakes are significantly higher. If you have any questions, please feel free to reach out. @Nate Herk , I hope it is okay for me to share this here. I do not want to interfere with the momentum of the group, but I believe this information is closely related and may be valuable to many members of the AIS community.

I’ve been watching our 3,700 students in AIS+, and I noticed the people making the most money are all doing this: https://app.aiautomationsociety.ai/10-hours The people charging $5,000, $10,000, even $50,000 per engagement weren't better builders. Before they ever opened n8n/Claude Code, they did one thing differently: → They found the automations worth building first. It’s like a mini audit. Just by asking a few questions and mapping out the opportunities, they were able to get clients excited and also choose the right projects to work on. And the best part is you can practice by running this same system on YOURSELF. I call it 10 Hours to 10 Seconds, because doing this can easily save you or your clients 10 hours a week by automating the right things. Get all the details here: https://app.aiautomationsociety.ai/10-hours Talk soon, Nate PS: If you’re in AIS+, this has already been updated and provided to you at no cost. You can find it in the classroom

Feels like every second post is med spas and real estate. Meanwhile I’m over here building stuff for: • Bike shops • Kids Book creators • Supplement brands • AI receptionists for fireplace companies Is it just me or is the real world random AF! 😂