Think Slowly.
See Farther.
Essays and field notes on what stays hard when AI makes code cheap: context, judgment, evaluation, and how teams of people and agents actually work. Each piece argues one claim. Written by a data and AI builder with more than two decades in software and analytics.
Thread 1
Context & memory
How separate AI sessions coordinate without pretending to share a mind.
Essay 10 min read
Shared Context Without Shared Memory
Two independent AI conversations can coordinate without pretending to share a mind—if people give them the same versioned, reviewed context contract.
Read the essay →Thread 2
Judgment & evaluation
Knowing what good looks like, and building checks that can tell.
Code is cheap. Taste, intent and eval are not.
Essay 7 min read
Code Is Cheap. Taste, Intent, and Eval Are Not.
The scarce skill for AI-native developers is no longer just writing code. It is knowing what good looks like, expressing intent clearly, and building mechanisms that can tell whether the result actually works.
Read the essay →Thread 3
Agents & organizations
What changes when agents join the team as coworkers.
An AI-native company treats agents as team members, and that rewrites hiring, trust and management.
Essay 12 min read
Organization Theory for the AI Era
AI-native companies are not simply companies that use AI tools. They are organizations that treat agents as team members, which changes hiring, onboarding, permissioning, trust, evaluation, and management.
Read the essay →
