Long-form
Agency Branding on a Claude Code Budget. Claude Design in Practice
How much design can you do with AI, when you know nothing about branding?
Writing
Here is what I was trying to figure out. Here is what I found.
Technical writing on building technology, AI agent patterns, the economics of software, and the work of senior technical leadership. Long-form pieces publish when ready. Field notes keep the cadence warm.
Long-form
The Rise of Personal Software
Last week I laid out the hidden costs of your SaaS stack — the conformance tax, the integration tax, the simple math showing that adapting to someone else’s software often costs more than building your own.
Long-form
The Economics of a Dying SaaS Market
The average company spends $4,830 per employee per year on SaaS.
Long-form
Surface, Oracle, Ratchet: The Pattern Inside Karpathy's Autoresearch — Applied to Code
Karpathy's autoresearch paper describes a three-part pattern that shows up everywhere agent systems work. I found the same pattern in how I use Claude Code.
Field note
SOC2 Ready in a Day: How I Built a Complete Compliance Kit with Claude Code
I built a complete SOC 2 Type I compliance kit in a single working day using Claude Code. The deliverable was real — 12 policies, risk register, evidence index.
Field note
I Live in the Terminal. I Stopped Telling Others to Join Me.
I used to think everyone should work in the terminal. I was wrong about that, and the reason I was wrong matters more than the conclusion.
Long-form
How to Build a Claw That Won't Eat You
Agent systems have a failure mode that looks like success until the system turns on you. The pattern is predictable and the fix is structural.
Long-form
Trajectory: Teaching Claude Code to Learn Without Touching Model Weights
An experiment in persistent learning for Claude Code — building memory, context, and improving behavior across sessions without fine-tuning.
Long-form
ReAct Model
An examination of the ReAct pattern for language model reasoning and action, and how it shapes the way we build agent systems.
Field note
Using GPT3 to Build Zero-Shot Recommendation with Whisky Tasting Notes
A practical exploration of zero-shot recommendation systems using GPT-3 embeddings, applied to whisky tasting notes as the test domain.
Field note
Rethinking Search with ChatGPT
How conversational AI changes the mechanics of search, and what that means for the systems we build around information retrieval.