Playbooks

Answer guest inquiries with a quote: a reservations agent rule that moved prices into 92% of replies

Hotel Pirin's reservations agent answers new guests by email, Messenger and WhatsApp in the guest's language. On 24 September it was told to quote as soon as it had the dates and the party. The share of its replies that carried a price went from 50% (9 of 18) to 92% (33 of 36), and the median first reply was 41 seconds.

Published by Sellinger AI. Numbers and settings checked on 19 October 2026 against the fact register. Report an error.

median first reply over 54 guest inquiries (Messenger 12 s, email 49 s)
41 s
share of agent replies with a price, before and after 24 September
50% to 92%
agent answers to a guest came within 2 minutes
122 of 123
reservations created by the agent. Staff, the website or the owner's reply desk made every booking
0

The scenario

Families and couples write at any hour and go cold quickly. Before the quote rule, families with two or more children were handed to a colleague who would send an offer, and those offers took from 3 hours to 7 days. Of 473 threads read by hand, 63 were leisure guests asking about a new stay.

The configuration

  1. 1

    Guest writes

    Answer first

    In the guest's language. 22 of 54 inquiries were not in Bulgarian.

  2. 2

    Dates or ages missing

    Ask for them in the first reply

    No stalling and no handing over for a missing fact.

  3. 3

    Dates and party known

    Quote

    From live availability, or from the official rate card if the check fails. The total for the stay, what is included, how children are priced, the deposit, the cancellation terms and a way to book.

  4. 4

    Groups, agencies, Booking.com

    Staff

    These go to staff by design.

  • Never invent an unknown fact. The agent checked live availability in 30 of the 54 guest threads. In 5 of those the check failed and it priced from the rate card; all 5 totals were recomputed and matched, though one missed a 3 night discount.
  • Relevance scored 3.73 before and 4.33 after the rule, next step clarity 2.82 and 3.95 (1 to 5, on 22 and 43 scored replies).

The result

Leisure guests by who replied first
The agent, no staff before the booking322
The agent, then staff or the owner204
Staff only102
Nobody10

Of the 63 leisure guests, 8 booked. Not a causal comparison: staff join threads that already look promising. Seven reservations followed an agent's first reply.

What to claim, and what not to

  • Claim: the agent answers guests in under a minute, day and night, and quotes as soon as it has the dates and party.
  • Do not claim: that it closes bookings. People closed most of them.
  • Put a clock on every handoff. After a guest was handed to staff, the wait ran from 3 hours to 14 days.
  • Do not use one hotel's result as independent proof.

Common questions

Why quote immediately?
Before the rule only half of replies carried a price and guests waited hours for an offer. After it, 33 of 36 replies carried one.
Does the agent use the WhatsApp Business API?
No. It used a connected WhatsApp account and only answered guests who wrote first.
What if availability cannot be checked?
It prices from the official rate card, and the totals were recomputed and matched in all 5 cases.
Who closes the booking?
People did. The agent created no reservation.

Sources and method

A playbook here is a configuration that ran, with the outcome it produced and the base of every number. It is not a template promise: your audience and offer decide your own rates. Source: Hotel Pirin case study, guest threads from 1 June 2026, read by hand, snapshot 11 October 2026.

Related: Hotel Pirin case study, inbound lead qualification, WhatsApp agent, all playbooks.

From the blog

See it on your own accounts

Start with a 30 day free trial, no card. Nothing is sent without your approval unless you turn that on.

Unit4ShellyRocket.ChatGetAcceptPeopleForce

Teams that have used Sellinger

Start free trial