Our Thinking
Perspectives on AI, expertise, and why the hard problems matter most.
April 13, 2026 · Mark Freedman & William VanBuskirk
Your Agent Instructions Are Describing, Not Prescribing
System prompts, CLAUDE.md files, cursor rules — almost all agent documentation describes the world. But the document your agent actually needs is the one it can't derive from the code: your intent.
April 11, 2026 · William VanBuskirk
Your AI Agent Doesn't Have a Memory Problem. It Has an Architecture Problem.
A new research framework argues the next wave of agent capability won't come from bigger models — it will come from better infrastructure around them. We've been building on exactly this thesis.
April 10, 2026 · William VanBuskirk
The Complete Harness: Why Most AI Agents Are Only One-Third of the Solution
Everyone's building harnesses now. But most are incomplete — they do one thing well and pretend the other dimensions don't exist.
April 9, 2026 · William VanBuskirk
Why Your AI Agent Needs Dimensions, Not Just Skills
Most AI tools organize knowledge in a big bucket. But no one's actual job looks like that — jobs are multi-dimensional, and your agent architecture should be too.
Tell us what’s broken.
We’ll show you what’s possible.
Every conversation starts with your problem, not our pitch. Book 30 minutes and we’ll explore whether myai fits.