What does Team Size under Coordination Overhead conclude, in numbers, about “The Parallel Ceiling of an Agent Squad: How Many Volumes per Wave Pay Best”?
Answer: 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.
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.
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: 6.78, 89.6
| n | C(n) | per agent | marginal | channels | cost/volume |
|---|---|---|---|---|---|
| 1 | 1.00 | 1.000 | +1.000 | 0 | 1.000 |
| 2 | 1.79 | 0.893 | +0.786 | 1 | 1.120 |
| 3 | 2.34 | 0.781 | +0.558 | 3 | 1.280 |
| 4 | 2.70 | 0.676 | +0.359 | 6 | 1.480 |
| 5 | 2.91 | 0.581 | +0.204 | 10 | 1.720 |
| 6 | 3.00 | 0.500 | +0.093 | 15 | 2.000 |
| 7 | 3.02 | 0.431 | +0.017 | 21 | 2.320 |
| 8 | 2.99 | 0.373 | -0.032 | 28 | 2.680 |
| 9 | 2.92 | 0.325 | -0.063 | 36 | 3.080 |
| 10 | 2.84 | 0.284 | -0.081 | 45 | 3.520 |
| capacity peak n* = sqrt((1 - a) / b) = 6.78 | |||||
| 4 agents reach 89.6% of the peak capacity 3.017 | |||||
| agent cost k = 0.10 solo-volumes: economic size 5 | |||||
| agent cost k = 0.15 solo-volumes: economic size 5 | |||||
| agent cost k = 0.25 solo-volumes: economic size 4 | |||||
| agent cost k = 0.40 solo-volumes: economic size 3 |
Show the full program
# Chapter 4. p41: how many parallel writing agents per wave.
# Illustrative scene: the bureau runs volumes in parallel waves; one
# agent alone delivers one gate-green volume per wave. Contention
# a = 0.08 (shared gate runs, the coordinator reading each report) and
# pairwise coherence b = 0.02 (shared rules, locks, cross-checks) are
# illustrative, not measured. Capacity C(n) as in p32. The cost of one
# more agent is k solo-volumes per wave; the economic size is the
# largest n whose marginal capacity still exceeds k.
import math
A, B = 0.08, 0.02
def cap(n, a=A, b=B):
return n / (1.0 + a * (n - 1) + b * n * (n - 1))
if __name__ == "__main__":
print(" n C(n) per agent marginal channels cost/volume")
for n in range(1, 11):
c = cap(n)
print(" {:2d} {:4.2f} {:9.3f} {:+8.3f} {:8d} {:11.3f}"
.format(n, c, c / n, c - cap(n - 1) if n > 1 else c,
n * (n - 1) // 2, n / c))
peak = math.sqrt((1.0 - A) / B)
print("capacity peak n* = sqrt((1 - a) / b) = {:.2f}".format(peak))
print("4 agents reach {:.1%} of the peak capacity {:.3f}".format(
cap(4) / cap(7), cap(7)))
for k in (0.10, 0.15, 0.25, 0.40):
best = max(n for n in range(1, 30)
if n == 1 or cap(n) - cap(n - 1) >= k)
print("agent cost k = {:.2f} solo-volumes: economic size {}"
.format(k, best))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 4: The Parallel Ceiling of an Agent Squad: How Many Volumes per Wave Pay Best. 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
- Chapter 1 · Ringelmann's Two Sets of Numbers: Where "Half at Eight" Comes From and What the Rope Experiment Says
- Chapter 2 · Brooks's Law: n(n-1)/2 Channels and the Newcomers on a Late Project
- Chapter 3 · Serial Fractions and Pairwise Coherence: Amdahl's Ceiling and the Optimal Size under the Universal Scalability Law
- Chapter 5 · Merge Conflicts as a Birthday Problem: Shared Files, Hot Files and Private Directories
- Chapter 6 · Work Tables and the Pruning of Channels: Mesh, Star, Cells and Longest Job First
- Chapter 7 · Classical Sources East and West: "Working in Common Is Slow" in the Lüshi Chunqiu and Ringelmann in 1913
- Chapter 8 · Closing the Loop: Agent Squad Ceilings, Work Tables and a Pre-Registered Test