What does Closing Conversations, Objections and Hand-Overs conclude, in numbers, about “When an AI Sales Agent Hands Over to a Human: Gittins Indices and Ranking by Uplift”?
Answer: Chapter 5 allocates human time among sources of leads with Gittins indices (an exploration bonus of +0.102 for a new source) and finds that handing over the "hottest" conversations uses only 55% of the humans' potential.
Scope of the numbers: Priors, answer probabilities, close rates, refund rates and costs are illustrative or synthetic; all data are generated by its programs; the book is not legal advice and offers no scripts for manipulating buyers. Marked boxes separate published evidence, runnable Python calculations (16 programs), classical sources and the author's hypotheses.
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: 0.102
| source history | mean | Gittins index | exploration bonus |
|---|---|---|---|
| new (1 of 5) | 0.200 | 0.302 | +0.102 |
| 2 of 10 | 0.200 | 0.257 | +0.057 |
| 4 of 20 | 0.200 | 0.230 | +0.030 |
| 10 of 50 | 0.200 | 0.213 | +0.013 |
| 3 of 10 | 0.300 | 0.365 | +0.065 |
| 6 of 40 | 0.150 | 0.164 | +0.014 |
Show the full program
# Chapter 5. p09: Gittins indices for routing scarce human time. Leads come
# from several sources (campaigns, channels); each source has an unknown
# rate at which an escalated lead closes with a human closer. Each
# escalation is one pull of a Bernoulli arm with a Beta(a, b) posterior;
# rewards are discounted by 0.9 per escalation. The Gittins index is the
# retirement reward per step that makes stopping and continuing equally
# good (calibration by bisection, value iteration truncated at depth 80).
from functools import lru_cache
BETA, DEPTH = 0.9, 80
def index(a, b):
lo, hi = 0.0, 1.0
for _ in range(30):
lam = (lo + hi) / 2
ret = lam / (1 - BETA)
@lru_cache(maxsize=None)
def V(x, y):
p = x / (x + y)
if x + y - a - b >= DEPTH:
return max(ret, p / (1 - BETA))
go = p * (1 + BETA * V(x + 1, y)) + (1 - p) * BETA * V(x, y + 1)
return max(ret, go)
p = a / (a + b)
go = p * (1 + BETA * V(a + 1, b)) + (1 - p) * BETA * V(a, b + 1)
if go > ret + 1e-12:
lo = lam
else:
hi = lam
return (lo + hi) / 2
if __name__ == "__main__":
print(" source history mean Gittins index exploration bonus")
for a, b, label in ((1, 4, "new (1 of 5)"), (2, 8, "2 of 10"),
(4, 16, "4 of 20"), (10, 40, "10 of 50"),
(3, 7, "3 of 10"), (6, 34, "6 of 40")):
g = index(a, b)
m = a / (a + b)
print(" {:<16} {:5.3f} {:13.3f} {:+.3f}".format(
label, m, g, g - m))Single source and citation
Fan, Y. (2026). Conversational Closing Automata, Objection-Handling Information Gain and High-Ticket Sales Kinetics (Version 1.0.0), Chapter 5: When an AI Sales Agent Hands Over to a Human: Gittins Indices and Ranking by Uplift. 5D Library. https://doi.org/10.5281/zenodo.24090221
DOI: 10.5281/zenodo.24090221 · Read the monograph · 5DL-B-084 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026084,
author = {Fan, Yafu},
title = {Conversational Closing Automata, Objection-Handling Information Gain and High-Ticket Sales Kinetics},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
doi = {10.5281/zenodo.24090221},
url = {https://doi.org/10.5281/zenodo.24090221}
}Other chapter answers in this book
- Chapter 1 · What the Buyer Hides, and How Much Each Question Tells
- Chapter 2 · Diagnostic Question Trees: Which Question, and How Many
- Chapter 3 · Decoding the Four Classic Objections with Bayes
- Chapter 4 · The Books of High-Pressure Closing: Refunds, Chargebacks and Reputation
- Chapter 6 · Trust-Threshold Stopping Rules and Planning the Human Desk
- Chapter 7 · The Guiguzi's "Fan Ying" and "Nei Jian", and Su Qin's Persuasion of Qin in the Zhanguo Ce
- Chapter 8 · A Ledger of Ten Thousand Conversations, Probability Calibration and a Pre-Registered Experiment