Inside Nathan's Second Brain: Daniel Miessler, Security Expert & Creator of PAI, Audits My AI Setup

**Nathan Labenz** (0:00)
Hello, and welcome back to The Cognitive Revolution. Today, I'm excited to welcome Daniel Miessler, security researcher and founder of Unsupervised Learning, back for his second appearance on the podcast. Back in January, we discussed his personal AI infrastructure framework, and since then, taking inspiration from him and others, I've built my own. So this time, I share the details of what I've built and get his take on everything from the mental model that I'm using to relate to my AIs, to the steps I can take to continue to improve my security, to the process of continually improving the system, and beyond. As a preview, I would broadly break my AI stack into two main parts. The first is an instance of Claude Code that runs on my main personal laptop, with full access to information and accounts. I consider this to be an extension of myself, and as such, it does only what I tell it to do.
It took a significant investment to assemble all of the context needed to really make this work, but at this point, I have a 1GB database that contains the last five years of my digital history, spanning emails, calls, podcasts, social media content, and DMs across platforms, plus a layer of monthly, annual, and topic level summarization. With all that information available for fast local search, Claude can find just about anything I need it to find, even if my own memory has grown hazy with time. It really is amazing. If you're interested in setting something like that up for yourself, I created a public repository on my GitHub, where you can find linked in the show notes, containing the core tools and processes that you'd need to get started.
The second part of my setup is admittedly a lot more experimental. Taking inspiration from Daniel, Jesse Janay, and countless others, I've also created two new AI employees, one powered by Claude Code and one by OpenClaw, which are intended to act more autonomously based on my high-level direction. Now, I've never previously named an AI, but knowing that these agents will need to interact with humans and other AIs in order to accomplish bigger projects on their own, I finally broke down and gave them names. I'm calling my Claude Code instance, Aid, while the OpenClaw is Clay. I chose those names to reflect the roles I want them to play and the fact that I'm ultimately responsible, both for their nature and their behavior. And I'm spelling both with an AI, both as a hint to others and as a constant reminder for myself.
Infrastructure-wise, these agents live on a new entry-level Mac Mini, which is always on, regardless of whether I'm home or on the road. To access it remotely, I'm using Tailscale to create a virtual private network to which only my two computers and my iPhone belong. On top of that, I'm using Apple's native screen sharing when I need to log in to the Mac Mini from my laptop, the Screens app when I need to log in from my phone, and the Termeus app when I want to issue command line commands from mobile. All of this ensures that I can log in and reset things if something crashes or whatever else the case may be. But the real interface that I use most these days is a custom agent messaging app built for me by Claude Code, which allows me to send requests to agents on the go and also allows them to work together. The autonomous agents have their own Gmail, GitHub account, and heavily restricted Mercury virtual credit cards, but this communication layer allows them to ask my main laptop Claude Code for additional information or ask me for permission to use my accounts when needed.
Importantly, while I can access the Mac Mini and control agents from either the laptop or phone, this message system is the only way that the autonomous agents can reach out to us. They do not have access to the full deep context that lives on the laptop. It took again a lot of exploration and iteration to arrive at this setup, and I'm still constantly improving it. But at this point, it is working well, and as such, I am actually starting to achieve my 2026 goal of getting away from my desk and spending more time outside. As an example of the scale of project that such AI employees can handle, this coming week, Prokosh and I are going to do daily AI in the AM live shows Monday through Thursday. So, after having my laptop Claude Code, which remains unnamed, scanned my email for interesting guest possibilities, I gave a list of 25 potential guests to aid and let it manage the communications and scheduling process. Believe it or not, it's booked a full week's worth of guests without embarrassing us, and I think without most people even realizing that they're talking to an AI.