Zeno

The Concurrency Curve

Your attention has a peak. The evidence keeps pointing near four.

Add a second agent and you get more done. Add a fifth and you start losing the thread. Effective output rises with parallelism, then the cost of holding it all in your head takes over. The turn looks like it lands near four - and not just for agents. Screens, live conversations, objects you track at once: early evidence points at the same shape, the same neighbourhood. We did not pick four for agents; a century of attention research keeps landing nearby, which is exactly the claim we are now stress-testing.

Cognitive throughput versus number of parallel streams An inverted-U curve. Output rises with added parallel streams to a peak near four, then declines. PEAK parallel streams (N) effective cognitive output
Domain
AI agents under supervision
Peak at
N = 4measuring
Signal
RTLX-S supervision load climbs steeply once you pass ~4 parallel agents.

Curve shapes here are illustrative defaults. The exact per-domain numbers are being sourced from the deep-research questions below - and, for agents, from your own Zeno sessions.

The same shape, four ways

AI agents ~4

Supervising parallel coding agents: throughput climbs, then the babysitting tax - context-switching, verification, re-prompting - dominates.

Zeno RTLX-S supervision-load curve · your data calibrates it

Working memory ~4

The number of independent chunks you can hold and manipulate at once. Tracking moving objects tops out in the same place.

Cowan 2001, "the magical number 4" · Pylyshyn & Storm 1988 (MOT ~4-5)

Screens ~4

Monitored displays in a control room or trading desk: detection and vigilance degrade as the wall of screens grows past a handful.

Supervisory-control span · vigilance literature (research pending)

Conversations ~3

Simultaneous live chats a support agent can hold before response time and quality fall. The floor of active talk is even lower.

Contact-centre concurrency · media-multitasking cost (research pending)

The claim, stated carefully

Human parallel-supervisory capacity is not infinite and not linear. Across domains that look unrelated - memory chunks, tracked objects, monitored screens, simultaneous conversations, supervised agents - effective output follows an inverted-U that peaks at a small, strikingly similar number. Our working hypothesis: the peak is a property of human attention, not of the thing being supervised - and R5 below is us trying to break that claim, not just assert it. If it holds, agents are simply the newest stream to hit the ceiling, and Zeno's job is to measure where your peak sits, on your real workload, instead of guessing.

What we are researching next

The curve above ships with defensible defaults. These are the open questions that will replace them with cited, domain-specific numbers - and decide exactly how hard we can make the cross-domain claim. Full prompts in docs/RESEARCH_PROMPTS_CONCURRENCY_2026-06-14.md.

  • R1 - Capacity ceiling. Cowan's 4 vs Miller's 7±2 vs MOT vs subitizing: what is the consensus peak, and is the curve plateau-then-decline or monotonic?
  • R2 - Screens. Where does detection/vigilance performance peak as monitored displays grow (control rooms, SOC, drone operators)?
  • R3 - Conversations. The measured concurrency at which live-chat support quality peaks then falls.
  • R4 - Span of control. Sheridan supervisory control + Olsen/Goodrich fan-out (fan-out = neglect time / interaction time) mapped onto agent supervision.
  • R5 - The invariant. The strongest version of "the peak is a constant of attention" - and the strongest counterargument.
  • R6 - Your peak. The curve-fit (inverted-U / Yerkes-Dodson) that locates each user's personal peak-N from RTLX-S + session telemetry.

Find your number

Zeno measures the supervision cost of your AI-assisted work and renders your personal concurrency curve from real sessions.

See how it works Compare 4 styles Read the whitepaper