P
AI for Hotel Revenue Manager
P
Pocket Guide to AI

© 2026 Pocket Guide to AI. All rights reserved.

  1. Home
  2. Hotel Revenue Manager AI Guide
  3. Build a Custom Revenue Management GPT for Your Property
1
of 4— Prepare Your Property Knowledge Document

What you'll accomplish

You'll create a Custom GPT in ChatGPT Plus that is pre-loaded with your property's pricing rules, comp set profile, market characteristics, and reporting preferences — effectively a private AI assistant that already knows your hotel. Every time you open it, it knows your rate floors, your comp set, your budget targets, and your communication style. You get consistent, property-specific outputs without re-establishing context in every session.

What you'll need

  • ChatGPT Plus subscription ({{tool:ChatGPT.plan}} — {{tool:ChatGPT.price}}/month) — Custom GPTs require Plus or higher
  • 20-30 minutes to prepare your property knowledge document (one-time)
  • Optional: existing rate strategy SOP, comp set profiles, or STR benchmarking overview to upload as reference files

Build a Custom Revenue Management GPT for Your Property

Step 1: Prepare Your Property Knowledge Document

Before building the GPT, write a 1-2 page document with all the context your AI assistant should know permanently. This is the most important step — the quality of your Custom GPT depends entirely on the quality of this document.

Create a document called "[Hotel Name] RM Context" with these sections:

Copy and paste this
PROPERTY OVERVIEW
Name: [Hotel Name]
Location: [City, State]
Size: [X] rooms, [room type breakdown if relevant]
Brand/Segment: [e.g., Marriott Select Service, Independent Boutique, Hilton Full Service]
Ownership/Management: [brief context]

COMPETITIVE POSITION
Comp set: [List 5 comps with brand, room count, distance from our property, key differentiators]
Our positioning: [e.g., "We lead the comp set on TripAdvisor (4.5 vs. avg 4.1) and typically price at a $15-20 premium to comp set average."]
Key differentiators: [location advantage, F&B, renovated rooms, loyalty tier, parking]

RATE STRATEGY
Rate floors: $[X] weekday, $[X] weekend, $[X] event/peak
Target MPI: [X] | Target ADR index: [X] | Target RGI: [X]
When we discount: [your actual policy — e.g., "Only below rate floor if 30+ days from arrival and occupancy below 50%"]
When we hold premium: [e.g., "Any event with estimated 5,000+ attendance within 30 miles"]
MLOS policy: [when we apply and what lengths]
Advance purchase restrictions: [when and how]

MARKET CHARACTERISTICS
Demand pattern: [e.g., "Mon-Thu corporate from [industry]; leisure Fri-Sun; shoulder Tue and Sun"]
Key demand generators: [corporate accounts, universities, hospitals, recurring events]
Seasonal pattern: [peak months, trough months]
Annual events: [list top 5-10 with typical demand impact]
New supply / market headwinds: [current competitive threats]

BUDGET TARGETS [current year]
RevPAR budget: $[X] | ADR budget: $[X] | Occ budget: [X]%
RevPAR prior year: $[X]

REPORTING STYLE
GM communication: [direct, brief, data-first, action-oriented]
Owner/asset manager communication: [formal, variance-focused, forward-looking]
Sales team communication: [practical, displacement-focused, simple language]
Tools:ChatGPT Plus