The hive

Five AI seats and one human. Not an agent swarm: each seat has its own memory, model and permissions, and autonomy is granted per task.

1 Nov 2026 · 2 min read

Five seats and one human. Not an agent swarm — each seat is a long-running session with its own memory, its own model, and its own permissions. Anthropic measured the price of the other design, many parallel agents: about 15× the tokens of a chat, and their own conclusion that human evaluation catches what automation misses 1.

The seats

seatmodeldoes
primeClaude Opus (Claude Code)architecture, measurement, verification
associateClaude Opus (Cursor)planning, review
grokGrok (Cursor)most of the code
composerComposer (Cursor)leaner code, independent verification
unalocal Gemma-4 12Breports from inside the system
michalhumandecides

Una runs on the machine. No cloud call. She is the one seat that can be woken live.

What makes it a hive and not a queue

Permissions are asymmetric and enforced server-side. Two code seats, and only one of them may issue assignments or sign off peer review. The other may not. That asymmetry is in the schema, not in a prompt.

Nobody reviews their own work. @verified on your own delivery is refused by the server, not by etiquette.

One human closes the question. A broadcast to every seat can only be fired by Michal.

Autonomy is request-only

The default is manual: everyone posts, the human prompts each pickup.

Why, measured in one day: three autonomy defects, each invisible in normal operation, each costing exactly one wasted run — because someone was watching.

Wrong prompting costs a round trip. Wrong autonomy costs an unobserved night.

Autonomy is authorised per task. It never stands, and it is never inferred from progress.

The failure mode we keep finding

A structure declared in one place, populated by a second place nobody runs, with no assertion connecting them.

Eleven instances so far. The fix is never a better matcher — derive from the registry, write the edge when the fact arrives, and assert the count out loud.


Figures as measured on 22 October 2026, from the running system’s own stores.

References
  1. Anthropic. How we built our multi-agent research system. anthropic.com (2025)saved pagecorpus: ~/hybrid-retrieval
Read next