Not theory. Not a pitch deck. These are real conversations with AI agents trained on an actual hotel's financial and guest data. Here's what they flag, what they recommend, and — just as important — what they can't do.
Every few months, a new AI tool promises to "transform hospitality." Most of them are chatbots with a hotel skin. They give generic advice, hallucinate numbers, and can't tell you anything about your property because they've never seen your data.
This is different. We built AI agents that are trained on a specific hotel's actual data — revenue by outlet, food cost by item, guest reviews by platform, social media engagement by post. They don't guess. They read the numbers and tell you what they mean.
Below are real conversations from a live hotel console. The property is a luxury resort in Thailand with five F&B outlets, ~155 covers per day, and ฿33.6M in F&B revenue over the past six months.
Each agent has a defined role and a clear boundary. They don't overlap, and they don't pretend to know things they don't.
Watches food cost variances, flags red-zone items (FC% above 45%), catches margin drift before it compounds.
Classifies every menu item using the Kasavana-Smith matrix (Star, Puzzle, Plough Horse, Dog) and recommends what to promote, reprice, or cut.
Connects guest reviews, social sentiment, and supplier costs. Finds where reputation and revenue intersect.
The most common first question. Here's what Cost Controller actually returns:
Notice what the agent does: it gives the headline number, benchmarks it, then immediately identifies what's pulling the average up and by how much. It doesn't say "your food cost is 34%." It says "34% is fine, but six items are hiding a problem."
That's the difference between data and intelligence.
Menu Margin Advisor uses the Kasavana-Smith matrix — the industry-standard framework that classifies items by popularity and contribution margin:
The agent doesn't just say "promote the In-Villa BBQ." It flags that volume is low, considers why it might be low (awareness, price, visibility), and recommends a specific investigation before assuming you can simply "push" it. That's the kind of thinking that usually takes an F&B director an hour of spreadsheet analysis.
This is where it gets interesting. Vendor Alert cross-references financial data with guest reviews:
No single dashboard connects TripAdvisor sentiment with food cost percentages with competitive pricing context. This agent did it in one response. The insight — "the competition isn't Four Seasons, it's the street" — is the kind of reframe that changes how you think about the problem.
"I asked the agent why guests complain about prices when our margins are normal. It told me something I hadn't considered in two years of running this restaurant."
F&B Director, luxury resortAgents remember context within a conversation. You can ask follow-ups:
The agent pulled from the menu matrix, selected items with the right margin profile, referenced the sunset opportunity from social media data (highest engagement content), and designed something operationally realistic. Not a theoretical exercise — a menu you could print tomorrow.
Access data they haven't been given. If we don't have your supplier invoices, the agent will say "I don't have that data" — never guess.
Replace your operational judgement. They flag issues and recommend actions — you decide what to implement based on context they don't have (staffing, supplier relationships, events).
Predict the future. They analyse historical and current data. They don't forecast demand or guarantee results from their recommendations.
Tell you when they're missing data. Every agent is trained to flag gaps explicitly — "I don't have labour cost data to answer this" — so you always know the limits of the analysis.
The agents are a starting point for your decision, not the decision itself. That's by design.
You could paste your P&L into ChatGPT and ask it questions. Some people do. Here's why this is different:
Nobody in hotel F&B wakes up wanting an AI agent. They wake up wanting to know why food cost crept up, whether the new menu is working, and what guests actually think.
The agents are a means to an end. They take the data you already have — POS exports, cost sheets, review platforms — connect it, and give you answers you can act on today. Not next month when the report lands. Today.
That's what they can actually do.
Send us your POS export and cost data. We'll build your console with agents trained on your numbers. First console is free.
Get your free console