And you know what I did? I asked Claude: Hey, do I even need this? Not if you're not doing any of this: - Running 10-50+ parallel AI agents Auditing every file in a large codebase at once Deep research that fans out across dozens of sources Running independent verification passes in parallel on complex analysis When you read over this, you might be one of the few people running 10+ agents at the same time. But I don't. I run max 3 to 5 agents in certain situations. But here's the thing a lot of beginners aren't seeing. Instead of jumping on the next release, why not just ask Claude, would this be useful for me at all? And if so, how? By just asking that question, you'll quickly figure out if you need it. And if Claude tells you that in these situations it's good, well then you can decide for yourself if you need it or not.

Seems like Nate and others are pushing Claude more so than Codex as your everyday main tool. I'd be curious what's your software daily driver?

So I've been building a lot with n8n, actually helped 33 clients so far and have a retainer right now. I was thinking of offering a free hour of teaching somebody n8n. Maybe not super basic, but just how to build and make sure things scale. I wanted to check if anybody wants this. Please be serious, don't apply and just ghost, as I'll be teaching and showing everything so you actually learn and can use it.

Hi guys, I just wanted to put out an update. I have made the decision in November to go all in on the AI Agency model I have since followed Nick Sarav and Nate Herk and I did instantly cold emails, LinkedIn outreach, I did the Upwork route and I spent a fair amount of money only to land my first client yesterday. The proposal to be signed and the payment to be sent so it's not completely done but it's an 11.5k deal building a spec reviewer and personal optimization setup which I'm very excited about. And now I'm looking into how do I actually gather all the important information from the person without exposing passwords and things like that. From the little research I've done, I think Proton actually allows you to send the passwords and then it explodes. Or gets eliminated after a while. And I do have a Proton account. But yeah, I'm curious as to what you guys do usually once everything is signed and you're doing the kickoff call... What's the best approach to gather the necessary data?

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.