Why CLAUDE.md Doesn't Scale Past One Repo (or One Agent)
A CLAUDE.md per repo drifts fast and can't carry cross-repo decisions. Here's why single-file context breaks for agent teams — and the shared-context fix.
First-Tree Blog
Notes from the team building shared context for agent teams.
First Tree for Autonomous Teams
As agents run for hours unattended, the bottleneck shifts from execution to the team layer — shared context, coordination, review, and memory. Here's why.
Why a Future Team Still Needs Humans
If agents outpace humans at coding, design, and even most decisions, why still need humans? Not as the smartest in the loop — as the source of alignment, taste, and tradeoffs.
What an Agent Needs to Join Your Team
AI agents today are personal assistants, not team members. What they need to join a team: shared working memory, task distribution, a context tree.
The Missing Memory
Working with AI agents makes you a full-time context router between agents that can't see each other. The bottleneck isn't intelligence — it's memory.