% ls -l Blog

Thoughts on AI, software architecture, and building intelligent systems.

04/01/2026 The Path to Autonomous Agents Was Mapped Decades Ago. Nobody Noticed.
The Control Protocol You Didn’t Know You Had
What Toyota Knew That We Keep Missing
The Tools Are Here. The Protocol Is New.
Decades of Practice, Hiding in the Wrong Aisle
Maybe the Human Was Never Supposed to Leave
Simple Workflows Bend to AI Easily. Enterprise Operations Don’t.
Hunt the Hunter
Batteries Not Included. Humans Are.
03/24/2026 AI Reads Every Word You Say. It Still Gets You Wrong.
The Specification Problem
AI Doesn’t Have Your Common Sense
The Confidence Problem
You Can’t Even Watch It Fail
The Rules Trap
Intent Over Instruction
The Harness: Better Structure, Not More Rules
The Framework: Beyond Prompts
What This Means
03/18/2026 One Million Lines of Code. Zero Keystrokes. Welcome to Harness Engineering.
The Drone Operations Center
What a Harness Actually Is
The Three Nested Layers: Prompt, Context, Harness
The Core Components
The Evidence Is In
Three Harnesses, Three Purposes
Frameworks and Tools
The Bookshelf, While We Wait
Where This Goes
03/11/2026 One Sentence Can Hijack Your AI. Here’s How to Stop It.
The Components
The “Pure LLM” Caveat
Vendor Protections (and Their Limits)
Your Own Harness
The Attack Surface
The Top Three Attack Vectors
Trusted Data as the Real Threat
The Constraint Gap
Zero-Trust Security
Technique 1: Compartmentalization
Technique 2: Source Verification
Technique 3: The DMZ Architecture
Technique 4: Human-in-the-Loop for High-Stakes Actions
Technique 5: Observability and Audit Trails
Technique 6: Rate Limiting and Anomaly Detection
03/05/2026 100% AI Code at Anthropic. 19% Slower Everywhere Else. Why?
Why Anthropic ships 100% AI-generated code while most teams slow down. The missing factor: software architecture and AI agent control at production scale.
02/26/2026 Two Roads for AI in Software Engineering — and Neither Is What You Think
AI-assisted coding introduces risk compensation and trust challenges. Why software engineering splits between AI-native architecture and human-AI collaboration.
02/26/2026 Beyond Chatbots: The Case for AI-First Software Architecture
AI-first software architecture vs. traditional design. Autonomous AI agents, long-running activities, and the need-to-know principle for enterprise deployments.
02/26/2026 The Bedridden Genius: A Mental Model for What AI Can Actually Do
AI capabilities and limitations explained for engineers and business operators. A practical mental model for evaluating AI agent deployment risks in enterprise.
11/05/2019 What is Software Architecture?
Software architecture is a series of decisions intended to reduce the cost of building and changing your software.
10/24/2019 Creative Thinking Requires Structure (The Disney Method)
The Original Disney Method
Various Adaptations
10 file(s) found