What does Computing the Rhythm of Private-Message Sales conclude, in numbers, about “First-Reply Latency: the Cooling Curve of an Inquiry, Night-Time Auto-Acknowledgements and Erlang C Staffing”?

Answer: Chapter 2 shows interest in an inquiry halving in about 63 minutes, with 6 agents needed for 40 inquiries an hour to keep waits over 5 minutes below 0.10.

Scope of the numbers: Its parameters are illustrative; all calculations are generated by its programs; it is not individual legal, compliance or business advice, and it discusses only closing that keeps the rules. Chapter 1 splits an illustrative 184-character quote by dynamic programming into 5 bubbles at a cost of 46.52, against 142.00 for one sentence per bubble.

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: 0.10, 40

inquiries/hagentsP(wait>0)P(wait>5min)mean wait (min)
2030.4440.1932.67
2040.1740.0330.52
2050.0600.0050.12
4050.5540.2413.32
4060.2850.0540.85
4070.1350.0110.27
8090.6530.2843.92
80100.4090.0771.23
80110.2450.0200.49
rule: smallest c with P(wait > 5 min) <= 0.10
Show the full program
# Chapter 2. p22: how many agents keep first replies under 5 minutes
# Model: Erlang C queue (M/M/c). Inquiries arrive at rate LAM per hour,
# each agent handles one conversation at a time with mean handling time
# 6 minutes (illustrative). P(wait > t) = C(c, a) * exp(-(c*mu - LAM) t),
# where a = LAM / mu and C(c, a) is the Erlang C probability of waiting.
import math

MU = 10.0          # conversations per agent-hour (6 minutes each)
TARGET_T = 5 / 60  # 5 minutes
TARGET_P = 0.10


def erlang_c(c, a):
    terms = [a ** k / math.factorial(k) for k in range(c)]
    last = a ** c / math.factorial(c) * c / (c - a)
    return last / (math.fsum(terms) + last)


def p_wait_over(c, lam, t):
    a = lam / MU
    if c <= a:
        return 1.0
    return erlang_c(c, a) * math.exp(-(c * MU - lam) * t)


def mean_wait_min(c, lam):
    a = lam / MU
    return erlang_c(c, a) / (c * MU - lam) * 60


print("inquiries/h  agents  P(wait>0)  P(wait>5min)  mean wait (min)")
for lam in (20.0, 40.0, 80.0):
    c = int(lam / MU) + 1
    while p_wait_over(c, lam, TARGET_T) > TARGET_P:
        c += 1
    for cc in (c - 1, c, c + 1):
        if cc <= lam / MU:
            continue
        print("{:>11.0f} {:>7} {:>10.3f} {:>13.3f} {:>16.2f}".format(
            lam, cc, erlang_c(cc, lam / MU), p_wait_over(cc, lam, TARGET_T),
            mean_wait_min(cc, lam)))
print("rule: smallest c with P(wait > 5 min) <= {:.2f}".format(TARGET_P))

Single source and citation

Fan, Y. (2026). Instant-Messaging Bubble Rhythm, Read-No-Reply Icebreaking Games and High-Ticket Closing in Private Messages (Version 1.0.0), Chapter 2: First-Reply Latency: the Cooling Curve of an Inquiry, Night-Time Auto-Acknowledgements and Erlang C Staffing. 5D Library. DOI pending

DOI pending · monograph page goes live after publication · 5DL-B-145 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026145,
  author    = {Fan, Yafu},
  title     = {Instant-Messaging Bubble Rhythm, Read-No-Reply Icebreaking Games and High-Ticket Closing in Private Messages},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

Other chapter answers in this book