I'm developing a voice-based AI agent for scheduling appointments. If you've done this before, what's your setup?

I hear some version of this constantly and it's almost always wrong. Not because the models are perfect because I know they're not. But because "is the model good enough" blames the tech rather than yourself. AI adoption isn't binary. It's not "can the agent do this entire job for me? Yes or no?" It's "how much can it do, how much do I need to guide it, and where does it still make me faster than I was?" Right now there's a massive gap in how people use this stuff. On one end, someone is running a business by themselves that used to take a team of 15. On the other end, someone opens the AI tool their company gave them, asks for some research, watches it hallucinate everything, closes it, and decides AI just isn't there yet. If everyone has access to the same models, then why are we seeing people get drastically different outcomes? Because if someone is getting great results from a setup you could copy today, the bottleneck isn't the model. It's the driver. The way I think about it, there are three layers: → The model is the engine. Opus, GPT, Gemini, whatever you're running. Everyone can buy the same one. → The harness is the car built around that engine. Claude Code, Codex, OpenClaw. The tools it can reach, the way it spins up sub-agents to split up the work, the whole system that turns a raw model into something that can actually do a job. → You're still the driver. Your prompts. The context you feed it. The memory and skills you set up so it knows how you work. And the steering, for when it starts to drift. You can put the car on cruise control. But if you don't steer, you're still going to crash. (Yeah, I know some cars have lane assist now. You get the point.) A while back, Andrew Ng ran a version of this. GPT-3.5, an older and "worse" model, wrapped in a simple agentic workflow, hit around 95% on a coding test. GPT-4 on its own, no workflow, hit 67%. That workflow is the harness. A better harness around an older engine beat a newer engine running on its own.

Anthropic just released a report called "When AI Builds Itself," where they reveal that more than 80% of the code they ship is now written by their own AI. I read through the whole thing and walked away convinced that AGI, at least by the definition that actually matters, is already here. This video breaks down the numbers from their internal data, the three ways things could go from here, and why the company building the most powerful version of this is the one telling us to slow down.

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

So I'm sure you guys have heard the term "AI slop", and everyone sorta defines it differently. Maybe you think it's those TikToks of AI-generated fruits going on dates. Maybe it's infographics with misspelled words. Maybe it's something else entirely. But I want to talk about it in the context of communication. Internal, external, content you put out into the world. I write my LinkedIn posts with AI. My agent knows my business, how I write, how I speak. That's just how I work now. And there's nothing wrong with that. I think everyone should be using AI to write if it makes them more efficient. But this isn't a binary yes or no. It's a spectrum. Sometimes AI can draft and send automatically. Most of the time, I want it to just draft. Then I review. If someone sends me an email with em dashes everywhere, I don't actually care at all that they used AI. The fact that I can clearly tell it's AI-generated isn't the problem. What I do start asking is: → Did they proofread this? → Is this completely accurate? And subconsciously, I might start losing trust. Not just in the email but in the person who sent it. Our job here has changed from writer to reviewer. This quote has really stuck with me: "You can outsource your thinking, but you can never outsource your understanding." When your name is attached to the content, you take credit if it lands, as you should. But that also means you need to take accountability if it's incorrect. Taste and reviewing are becoming more important than ever. AI is super intelligent and powerful, but I don't want to see a world where we trust AI so much, that we stop reviewing things, and then the human on the other end of the content starts losing trust in us. That's why even though I write with AI, and people know that, I still try my best to disguise it and make it sound as "Nate" as possible. Check out the LinkedIn post I just wrote about this HERE