What does Team Size under Coordination Overhead conclude, in numbers, about “Closing the Loop: Agent Squad Ceilings, Work Tables and a Pre-Registered Test”?

Answer: Chapter 8 gives the empirical loop for agent squad ceilings and work tables, the distilled Optimal Team Size Calculator and a pre-registered test: a ratio per member below 0.781 rejects the hypothesis of no loss. Marked boxes separate published evidence, runnable Python calculations (18 programs), classical sources and the author's hypotheses.

Scope of the numbers: Parameters are illustrative; all calculations are generated by the book's programs; the book is general business analysis, not individualised business advice. Chapter 4 takes this bureau's four volumes in parallel per wave as an illustrative scene: capacity peaks at 6.78 windows, four windows already reach 89.6 % of the peak, and the coordinator's review queue holds the ceiling at four.

中文版

Data table

The numbers below are printed verbatim by the chapter's Python program and can be reproduced by running it. standard-library Python onlyprinted values that match the answer: 0.781

z_a1.9600, z_b = 0.8416
delta sd0.15 sd=0.25 sd=0.40
0.3244 10 24
0.2009 25 63
0.10036 99 252
0.050142 393 1005
standardised d for human groups (sd1):
d0.2: 393 d=0.5: 63 d=0.8: 25
delta0.324, sd = 0.25: 10 waves per arm, se 0.112
reject 'no loss' if observed ratio < 0.781
Show the full program
# Chapter 8. p82: pre-registered test: waves needed per arm.
# Outcome: gate-green volumes per agent per wave. Arm 1 runs one agent,
# arm 2 runs four in parallel. Null: no loss (per-agent ratio 1.0).
# Model prediction (p41): 0.676. Two-sided alpha = 0.05, power 0.80,
# normal approximation per arm: m = 2 (z_a + z_b)^2 sd^2 / delta^2,
# where sd is the wave-to-wave standard deviation in solo units
# (illustrative). Second block: Cohen's standardised d for human teams.
import math
from statistics import NormalDist

Z = NormalDist()
ZA = Z.inv_cdf(0.975)
ZB = Z.inv_cdf(0.80)


def per_arm(delta, sd):
    return math.ceil(2.0 * (ZA + ZB) ** 2 * sd * sd / (delta * delta))


if __name__ == "__main__":
    print("z_a = {:.4f}, z_b = {:.4f}".format(ZA, ZB))
    print("  delta    sd=0.15  sd=0.25  sd=0.40")
    for delta in (0.324, 0.20, 0.10, 0.05):
        print("  {:5.3f}  ".format(delta) + "  ".join(
            "{:7d}".format(per_arm(delta, sd)) for sd in (0.15, 0.25,
                                                          0.40)))
    print("standardised d for human groups (sd = 1):")
    print("  " + "  ".join("d={:.1f}: {}".format(d, per_arm(d, 1.0))
                           for d in (0.2, 0.5, 0.8)))
    m = per_arm(0.324, 0.25)
    se = 0.25 * math.sqrt(2.0 / m)
    print("delta = 0.324, sd = 0.25: {} waves per arm, se {:.3f}"
          .format(m, se))
    print("reject 'no loss' if observed ratio < {:.3f}".format(
        1.0 - ZA * se))

Single source and citation

Fan, Y. (2026). The Ringelmann Effect and Brooks's Law: the Optimal Size of Teams and Agent Squads under Coordination Overhead (Version 1.0.0), Chapter 8: Closing the Loop: Agent Squad Ceilings, Work Tables and a Pre-Registered Test. 5D Library. DOI pending

DOI pending · monograph page goes live after publication · 5DL-B-322 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026322,
  author    = {Fan, Yafu},
  title     = {The Ringelmann Effect and Brooks's Law: the Optimal Size of Teams and Agent Squads under Coordination Overhead},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

Other chapter answers in this book