Can you make a video about agent loops and agent harnesses?
Loops have been interesting to play with. The simplest way to get started: before you go to bed, give your AI agent a goal, and have it loop every X minutes as part of achieving that goal — this solves the problem of a model finishing a goal too early, and lets you trade tokens/time for quality since it doesn't matter if it takes 8 hours while you're asleep. Example: I wanted to scaffold out possible structures for a free community, so I set a goal and had it loop every 15 minutes overnight — over about 8 hours that's roughly 32 independent passes, each consulting the master list of ideas so far and adding a few new ones, ending with a massive list of options. A second major use is loops for software optimization: set up a loop where every X minutes an agent spawns and tries to improve some metric you care about (like page load speed) on a live property — it's essentially 'auto-research in a box,' logging what it's tried before and improving a test metric over time. The downside nobody talks about much: loops burn a ton of tokens — creators pushing loops are often fine spending $2-3K/month on AI tokens, so if you don't have that kind of budget, it can be a rough way to work.
Thank you. I had a great rest last night and I'm on fire today. If you want to talk about consistency and discipline, the best way is to get 8 to 9 hours of sleep each night—it makes everything easier. You asked about making a video on how to create an AI appointment setter; that would help a lot. Are you referring to an AI voice agent? If so, check out my AI voice agent—search for it, as Googling my content helps boost my rankings. One of my daily updates videos appears there, and there's also Nick's AI net worth search, which is funny. Another option is the AI agent, probably the website agent I built, which does some setting for you—give it a try and let me know your thoughts.
When I make videos like this, I constantly balance how deep to go on one person’s question versus covering enough to help many viewers. That’s why I don’t go super deep on niche topics like AI agent orchestration from a phone—most people are dealing with more fundamental issues, like the ones Muhammad and Sam raised. It’s also a matter of top‑of‑funnel versus bottom‑of‑funnel content. My recommendation is to stop worrying about queuing tasks from your phone and instead focus on the actual bottom‑line ROI you’re generating with your current workflow. Many people try to apply AI agents to everything because it sounds cool, but in my own experience, only a small fraction of my most valuable actions over the past week involved agents. I do use them for preliminary research, scoping, scaffolding, or creating outlines, but the core revenue drivers—what actually makes me money—come from me, not the agents. The real ROI lies in simple, repeatable systems like Getting Things Done by David Allen: having a place to capture ideas, checking back to decide if something is actionable, and then working through a clear next‑action flow. It may sound boring, but that’s where the real secrets are—rooted in proven, past‑tested methods, not chasing the latest AI trends.
On the AI agents video: I was just on a podcast with my buddy Matt talking about this — I think the market is ripe for a counter-signal video right now. A counter-signal is when a market is moving hard in one direction, everyone's hyping something up ('this agent has 8,000 components and automates your whole life'), and you make a video pushing back on that narrative. I think we're getting close to that point with AI agent hype. On the day-in-the-life vlog: honestly, a day in my life is just me sitting here working, exactly like what I'm doing right now. I've always been against POV-style 'entrepreneur in Bali' videos — sure, you can be an entrepreneur in Bali, but that's not really the entrepreneurial part. The actual entrepreneurial work is strategy, reporting, monitoring growth, making decisions that improve projected ROI — and that's basically what I do all day, which doesn't make for a very visually exciting vlog.
Thanks for the request—I'd love to make a video on building a humanlike chatbot. Right now, the value of an AI assistant feels small because I can do tasks like scheduling appointments myself in just a few seconds, whereas earlier it would have taken much more day-to-day effort. The question is when the speed gap becomes so tiny that it's worth using an AI, or when the value becomes so high that I'd need an AI secretary. For me, it doesn't make much sense yet because I type extremely fast—about 186 words per minute—thanks to years of RuneScape grinding where I had to type the same thing repeatedly without copy‑paste. I'm also very fluid with computers and know hotkeys, so doing things myself is often faster than telling an AI to do them, especially given the current lag and the few words needed to prompt the model. That said, the landscape is changing: soon we'll be able to chain actions, so a single prompt could trigger dozens of steps like looking up flights, comparing costs, and booking them via APIs. We're approaching that point, but the models aren't there yet, which is why I've held back on chatbot videos. I will definitely build a humanlike chatbot for tasks like this in the future. A community member, Mehmud from Maker School, already sells Vapy chatbots and showed how powerful simple prompts can be, so a Vapy‑focused video might be worthwhile as well.