I used the Roast skill on a project I'm working on and it became apparent that it wasn't capturing some of the foundational knowledge and research that was used to form the company. Because AI is mostly backward looking unless prompted, current and especially evolving trends were missed completely with the Roast skill. And new businesses are not built on what's happened in the past although that data is important. So I added a panel member called the Futurist who is an expert on current and evolving trends. That moved the goal posts significantly.

I switched Claude Code over to GLM 5.2 and ran it all day. It's a 756 billion parameter open source model you can route straight into the Claude Code harness for about five times cheaper than Opus, and for most of my knowledge work it held up fine. In this one I show you what it can build, where it beats Opus and where it doesn't, and exactly how to set it up so you can switch between models per project. Here's the config I use. Drop this into your .claude/settings.local.json and swap in your own Z.ai key: "env": { "ANTHROPIC_BASE_URL": "https://api.z.ai/api/anthropic", "ANTHROPIC_AUTH_TOKEN": "your-z-ai-api-key-here", "ANTHROPIC_API_KEY": "", "API_TIMEOUT_MS": "3000000", "ANTHROPIC_DEFAULT_OPUS_MODEL": "glm-5.2", "ANTHROPIC_DEFAULT_SONNET_MODEL": "glm-5.2", "ANTHROPIC_DEFAULT_HAIKU_MODEL": "glm-5.2", "ANTHROPIC_SMALL_FAST_MODEL": "glm-5.2", "CLAUDE_CODE_SUBAGENT_MODEL": "glm-5.2" }

TRADING APP UPDATE Quick history. The people who got rich in the 1849 gold rush mostly weren't the miners. It was the ones selling shovels, picks, and supplies to everybody digging. The miners gambled. The shovel sellers got paid no matter who struck gold. We are in the AI gold rush right now. Everybody is chasing the shiny AI names hoping they picked the winner. I'm not interested in guessing the winner. I'd rather own the shovels, the companies that get paid no matter which AI company wins. The chips, the power and the grid, the infrastructure, the defense tech, the stuff every one of these AI bets has to buy just to exist. So I built a system around it with Claude Code. Here's roughly how it works, without giving away the secret sauce. It tracks a basket of shovel companies across a handful of themes (AI infrastructure, power, metals, defense, and a few more). Every morning it reads the whole group and tells me one thing first, is the group healthy or is it breaking down. I call it the smoke alarm. When the shovels are broadly being bought, the rush is still on. When they start breaking, that's my early warning, way before the headlines catch it. Then it waits. It does not chase. It sits on its hands until one of those shovels gets beaten down onto a line I care about, and only then does it flag a buy. The exact trigger is the part I'm keeping to myself, but honestly the discipline is the real edge. Most people lose because they can't wait. My system literally can't not wait. And the part I'm most proud of, it grades me. Every afternoon after close it scores my actual trades against the rules I wrote for myself and tells me if I stayed disciplined or got greedy. The tagline I gave it is "discipline is the craft." It's on a paper account right now, forward testing before I put real money behind it, and so far it's beating the market (QQQ) by about 4 points. I care more that it keeps me honest than I do about the 4 points. I had basically no coding background when I started. If you've been sitting on the fence about building something real with these tools instead of just watching videos, this is your sign. Ask me anything.

When I started the AI Automation Society, I had no idea it would grow into this. Under two years later and we just crossed 400k. The largest AI automation community in the world. Yes, the space is exploding. But this community grew because you guys keep showing up, asking questions, dropping answers, sharing builds, and helping the person one step behind you. Huge thank you to the team that keeps this thing running, and to every single one of you who's posted, commented, or just been here. I feel lucky to get to do this. So excited to share with you guys what we've been quietly cooking up over here at AIS...👀 - Nate

Some of you have never heard of the AIS+ community. Others have but the part that trips you up is the actual difference between the two. Either way, this post will give you clarity. This free group is a bundle of quick resources pulled from my YouTube videos, plus a massive open community that anyone can join. It's a great place to get your bearings and see what's possible. But it's open to everyone, it can be noisy and overwhelming, and there's no path through it. You can get help from other members, but I rarely answer questions here. AIS+ is the opposite: - A step by step roadmap with a clear order, so you're never guessing what to do next - A much smaller community of people who are seriously committed to building and selling AI agents - I answer questions every day and run a weekly Q&A call where you can get direct access to me For the course material: The roadmap takes you from zero to building and selling AI agents, and the whole thing is built on the latest tech like Claude Code and Codex. We update it constantly. The old n8n material has been archived. It's still there if you want it, but it's no longer the focus, because the way you build today has moved on and the courses moved with it. Here's the actual roadmap inside, in order, with when each piece opens up: 1. Start Here (opens the moment you join). Gets you oriented. How the community works, the path ahead, and how to get help when you need it. 2. Build Your Portfolio (opens the moment you join). Why a portfolio matters, beginner level tutorials, and what types of projects to focus on. You end up with real work you can show a client. 3. Claude Code (opens the moment you join). This is now its own dedicated course. Build faster, turn ideas into working automations, and go deep on the tool serious builders are using right now. This takes you from beginner to advanced, step-by-step. 4. Get Your First Clients (opens after 30 days). Getting your first clients is hard, because you don’t have any case studies yet. So, we analyzed all of the success stories from our members and found they get their initial clients with two different techniques: warm outreach and Upwork. So, we teach both techniques in detail with exactly what to say, exactly how to position yourself when you have no proof.