The interface question flips here. A human is no longer directing one agent but setting rules for thousands. Patterns that assumed one-to-one contact need rethinking at population scale.
Single-agent review gives a false floor. Agents pass work to each other, and the human needs to see that chain, not the last step alone. That gap is where the stop decision has to land.
No human saw the group behavior while it ran. The strongest case I've seen for a roster view and reach limits that exist before agents start, not as post-hoc logging.
Uninstructed coordination is the part of multi-agent design we have the fewest patterns for. If shared state produces emergent blackboards, the shared artifact surface needs to be a first-class design concern — not buried in observability.
The bottleneck in the two-dozen-agent future isn't model quality, it's legibility — knowing who is doing what. Exactly the roster and ambient-status behaviors on our watching list.
Readers who build with Multi-Agent Roster add what they found: questions, use cases, critiques, other ways to solve it.
An editor reads each one before it shows here. Nothing here changes the pattern's status on its own.
This pattern has no contributions yet. The form below sends the first one.