The journal.
Essays on what it takes to understand someone’s work: promises, people, what changed, and the mistakes we made building it.
Three places to start.
AI Agents Need a Living Understanding
Why finding the old email is not the same as knowing what happened next.
Which Promises Are Still Open?
An email says “sent,” but the file is missing. When is the work done?
Why First Contact Is Not a Relationship
A stranger writes “urgent.” Why did the assistant put it first?
Keep reading.
Living Understanding
What an assistant needs to know when the answer has changed.
- 4 min
Memento's Problem Was Never the Notes
AI agents are like the hero of Memento: they can't form new memories, so they live on notes. Better learning will help. But the notes still have to stay true.
- 6 min
Beyond the Knowledge Base: How a Company Learns to Understand Itself
Search can find the message. It can't always tell whether the work is done, who knows the answer, or what changed. What a Company Brain needs beyond search.
- 3 min
The Four Levels of Agentic Understanding
Remembering an old answer is easy. Noticing that it stopped being true is harder. Four things an AI assistant needs to do well.
- 3 min
Your Agent Needs a Model of Your World, Not a Longer Chat History
A chat history remembers what was said. It doesn't reliably know which meeting moved, who made a promise, or what changed afterward.
- 3 min
What Is an AI Chief of Staff?
What an AI Chief of Staff should actually do: know what's changed, prepare you for what's next, handle the follow-through and know when to ask.
World Model in Practice
Mistakes, fixes and everyday questions from building the World Model.
Building Team0
What we learned while making the Chief useful in real work.