Topic · 3 essays
Adaptive Software
- Code Over Config
- Layered Context: An Adaptive Memory Architecture for Agents
- Action Architecture: How Agents Act Safely
Essays · Frameworks · Field notes
Building in hard mode.
Unfiltered insights from a builder of products, teams, and organizations for those working in hard mode, with high stakes and no playbook.
Most constraints were set when a person had to do the work. Don't design tomorrow's experience around them.
Topics
Curated reading paths. Start with the anchor, read in order.
Topic · 4 essays
AI Acceleration
- Why You're Not Seeing the Gains From AI
- Few Companies Know What AI Transformation Means
- The Supercomputer in the Corner
Topic · 5 essays
Innovation Architecture
- The Incumbent's Dilemma: Why disrupting yourself is hard
- Paramedics, ER, and Surgeons: How to Structure 0→1 Teams for Speed & Certainty
- The Disruptor's Paradox: How Great Innovators Become Incrementalists...and What to Do About It
Recent
108 posts
The Paradox of Prudence
The decisions that stagnate growing businesses aren't the bad ones; rather, they're a series of individually smart ones that never compound.
Action Architecture: How Agents Act Safely
We've explored on this blog, systems that have a memory architecture, and how we can update that memory architecture to effectively "learn". Now, we explore how we can let agents run unsupervised safely. This is the final piece in the adaptive software architecture.
Sky's the Limit: a hands-on guide to agentic engineering
I recently introduced the "AI Adoption Continuum", that maps the proficiency of people & orgs. It uses a transportation metaphor, going from walking all the way to flying rockets. This tutorial aims to get you from "ground transportation" to "airborne" by showing how to build agent harnesses.
Archive
Newsletter
Scar tissue, delivered.
New essays on strategy, AI, and building — roughly twice a month. No filler.