Research & Writing

Mar 2026 Trump Doesn’t Bomb on Mondays Five major strikes, both terms, 100% landed Thursday or Friday. The pattern isn’t coincidence. 2026 Who Owns the Texas Power Grid? Interactive map: the companies controlling Texas power infrastructure are the same ones shaping its regulation. Mar 2026 Your AI Agent Doesn’t Have a Model Problem Everybody is asking which model to use. That is not the main question. The harness is the product. Mar 2026 The $300K/Month Agent: Why Felix Matters An AI agent generated $300K in a month. What actually happened and what it means for normal business owners. Mar 2026 How Local Businesses Get Recommended by AI The practical GEO playbook for local businesses that want to be recommended by AI, not just found by Google. 2026 Your Firm’s ChatGPT Problem Most RIA staff are already using ChatGPT for client tasks. That’s a live compliance exposure. 2026 The BYOA Problem Top performers are building personal AI agents — and when they quit, all that institutional knowledge leaves with them. Feb 2026 Two Weeks, No Sleep, and What I Actually Built Two weeks of all-nighters, one AI agent, and an operation that didn’t exist a month ago. Apr 2026 The Operational Brain — One AI That Knows Your Business Why the “get an agent” framing is wrong, how memory compounds, and what three years looks like. Apr 2026 Why I Tell Most Clients to Wait Before Automating Anything Automating the wrong thing first is worse than doing nothing. Three questions I ask before recommending anything. Apr 2026 The Incidents That Made Me Build Guardrails I Should Have Built First 78 CMA PDFs with blank addresses. An AI contacting 20 leads nobody asked it to contact. What happened. Apr 2026 What It Actually Takes to Run AI for a Dozen Businesses Version drift, silent failures, and why the economics only hold with a fleet model. 2026 How Agent Memory Actually Compounds Session memory dies. Structured memory compounds. What changes at 90 days vs. day one, and the discipline required. 2026 The Platform I Had to Rebuild Mid-Flight I built an agent platform, watched it become a liability, and migrated a dozen live clients without taking anyone offline. Feb 2026 I Run 4 AI Agents From One Telegram Chat Role specialization, routing discipline, and real operational throughput. Feb 2026 What I Learned Rebuilding an Agent Stack from Scratch Model degradation, why local LLMs failed in production, and the reset that fixed it. Feb 2026 Memory Architecture for Agents A 3-tier memory model that reduces drift and keeps context useful across sessions. Feb 2026 The Clean-Room Pattern: Cloud AI Without Leaking Data Cloud AI performance without exposing sensitive information to third-party servers. Feb 2026 Why a $20 Model Beats a $200 Model (If You Do This) The variable that drives agent performance isn’t the model tier. Mar 2026 Making Agents Run While You Sleep How asynchronous dispatch, checkpoints, and completion loops create overnight execution. Feb 2026 Fixing Agent Drift and Reliability How to recover from silent regressions and restore execution trust. Feb 2026 Agent Operating System Setup Roles, guardrails, and proof-first execution standards. Feb 2026 Skills: The Loadout System for AI Agents Why skills are the loadout layer that turns general models into dependable operators.