One of the unexpected joys of building a Personal AI Infrastructure is the moment you realize: this doesn’t have to live on just one machine. My PAI runs on a Windows workstation at home. It has all my context, my skills, my workflows, my history. But I’m not always at that desk. Sometimes I’m on my phone. Sometimes my daughter wants to use her Chromebook for homework help. The question became: how do I access PAI from anywhere? ...
What if your AI assistant could create images? Not generic stock photos or simple icons - but custom visuals that match your aesthetic, illustrate your ideas, and enhance your content. That’s what I built today: an Art skill for my Personal AI Infrastructure. This post is a show-and-tell of the images Pal created in our first session together, including the prompts that generated them. No technical tutorial - just a visual journey through what’s now possible. ...
Most AI tools treat every conversation like you’re a stranger. You explain your context, your preferences, your constraints—over and over again. PAI changes that. Personal AI Infrastructure (PAI) is a system that wraps AI with your context. It remembers your projects, knows your preferences, and can be extended to handle whatever you need. And the best part? It’s built on simple building blocks that anyone can understand and customize. ...
Every system I’ve built for my Personal AI Infrastructure stands on a foundation I didn’t create. That foundation comes largely from the work of one person: Daniel Miessler. This post is both a thank-you and a guide for anyone wanting to understand the incredible resources Daniel has shared with the world. Who Is Daniel Miessler? Daniel is a cybersecurity and AI engineer based in the San Francisco Bay Area who’s been writing online since 1999. He runs Unsupervised Learning, a newsletter and podcast read by over 95,000 subscribers including people at OpenAI, NVIDIA, Apple, and Google. ...
I have a demanding career. I manage customer experience analytics at Agilent Technologies. I teach at two universities. I’m building a consulting business. And I’m deeply involved in AI infrastructure development. But none of that matters if I’m not present for my family. My wife Tiffany and I have two daughters - Ellie (9) and Tessa (5). Between dance classes, swim lessons, gymnastics, and the endless logistics of family life, staying organized is a challenge. Staying present is harder. ...
I teach Data Programming in Python at the University of Iowa - a core course for Master of Science in Business Analytics (MSBA) students and an elective for MBAs. This spring, I’m collaborating with course owner Michael Redmond from Tippie College of Business to redesign the curriculum and teach something new: how to learn and code with AI assistance. The irony? I’m using AI to help me do it. ...
Email is broken. Not the technology - the experience. I have 18 email accounts across work, teaching, personal, and consulting contexts. Every morning starts with the same ritual: open each inbox, scan for urgent items, delete the noise, maybe respond to a few. Repeat. I built an AI agent to fix this. The Architecture The system has three layers: Outlook MCP Server - A Model Context Protocol server that exposes Outlook operations as AI-callable tools Outlook Skill - A Claude Code skill with workflows for common email tasks Email Organizer Agent - Higher-level automation for inbox cleanup and organization Why Outlook COM API? I chose Outlook’s COM API over cloud APIs (Graph, Gmail) for several reasons: ...
I’ve been building what I call Personal AI Infrastructure (PAI) for a few months now. This blog is where I’ll document the journey. The Problem AI tools are everywhere. ChatGPT, Claude, Copilot - they’re useful, but they don’t know me. Every conversation starts from scratch. Context gets lost. Work gets repeated. I wanted something different. An AI system that: Remembers past conversations and decisions Understands my projects, preferences, and constraints Runs locally when I need it to Integrates with my actual workflow The Approach I’m building on Claude Code as the foundation. Not because it’s perfect, but because: ...