Live
In production at our first partner brewery
Real-time
Each interaction sharpens the taste profile within seconds
Menu-grounded
Only recommends beers you're actually pouring — no hallucinations
Opt-in
Customers control their data; one-tap reversible
What an AI bartender actually does
The job of a great bartender is to remember what each regular likes, recommend something they'll love, and tell them when a new beer they'll go for hits the tap. Barley does that for every customer, at scale, every day.
Remembers every customer
As each guest engages — quiz, ratings, chat, claimed orders — Barley builds a taste graph: hop preferences, ABV range, can vs. draft, time-of-day patterns, repeat favorites.
Recommends what to pour next
Customer asks 'what should I drink?' or browses the menu — Barley suggests beers from your live tap list ordered by predicted taste match.
Speaks craft-beer fluently
Knows that Citra is tropical-dank, that lambics need explanation, that imperial stouts pair with cold weather. Generic LLMs guess; Barley knows.
Pings the right people on release
A new beer hits — Barley alerts the customers whose history says they'll love it. Segmented messaging, not blast.
Grounded in your menu
Recommendations only come from beers you're currently pouring or selling. Cannot invent beers, prices, awards, or specs.
Privacy-first by design
Customers opt in explicitly, opt out one-tap, and never have their data shared across breweries.
Generic AI chatbot vs. purpose-built AI bartender
Most "AI for hospitality" tools are a chat UI bolted to a general-purpose LLM. The differences show up the first time a customer asks something specific.
| Capability | Generic chatbot (ChatGPT-on-rails) | Barley |
|---|---|---|
| Knows what's actually on tap | No — invents beers | Yes — live menu only |
| Speaks craft taxonomy (IBU, dry hop, hop bill) | Surface-level | Native |
| Personalizes from real POS data | No | Yes — Square-driven |
| Updates in real time as a customer orders | No | Yes — within seconds |
| Sends segmented release alerts | No | Yes — taste-profile based |
| Privacy guarantees per brewery | Unclear | Per-customer opt-in, scoped to brewery |
| Grounded — cannot invent specs or prices | No — common | Yes — menu-grounded |
How Barley learns
Four data sources combine into one taste graph per customer. The graph powers every recommendation, alert, and dashboard insight.
- 1
Square POS — the foundation
Your catalog and transactions ground the system: which beers you pour, what's selling, how each release performs, by time and location. It's the product-level intelligence the taste graph builds on — all from data you already have.
- 2
Menu metadata — the taxonomy
When a beer hits your menu (in Square or in Barley), you describe it in craft-beer terms: style, ABV, IBU, hops, malt, ferment style. Barley uses these features for cold-start recommendations.
- 3
Customer interactions — the chat layer
When a customer chats with Barley (web or in-taproom), every preference they share — 'I'm not into sours', 'I want something hoppy under 7%' — becomes part of their taste graph.
- 4
Aggregate, anonymized patterns
At the model level, Barley learns universal patterns ('people who like Hazy IPAs often like New England Pales'). Per-brewery and per-customer data is never shared cross-brewery; only the abstract patterns travel.
The Beer Taste Genome
Music Genome Project, for craft beer.
Every beer Barley sees gets a structured profile across roughly 30 sensory and contextual dimensions — style, hop bill, ABV band, bitterness, sweetness, body, freshness window, food pairings, and more. None of this is hand-coded prompt engineering. It's the structured menu data that drives every recommendation.
Style
- Hazy IPA
- West Coast IPA
- Imperial / Double IPA
- Pilsner
- Lager
- Stout
- Imperial Stout
- Saison
- Sour
- Lambic
- Porter
- Wheat / Hefeweizen
Hop profile
- Citra
- Mosaic
- Galaxy
- Simcoe
- Centennial
- Cascade
- Amarillo
- Nelson Sauvin
- Idaho 7
- Sabro
Strength & character
- ABV bands (sub-5%, 5–7%, 7–9%, 9%+)
- IBU range
- Dry-hopped vs. not
- Barrel-aged
- Fruited
- Brett character
- Coffee / vanilla / chocolate adjuncts
- Sessionable vs. sipper
Drinkers like you
iTunes Genius, for beer.
The Beer Taste Genome knows the beer. Collaborative filtering knows the drinkers. Barley lines your ratings up against everyone whose taste overlaps with yours and surfaces the gap — “you’re missing this, and people who drink like you love it.” It’s the engine behind iTunes Genius and Netflix’s “because you watched,” pointed at the tap list and scoped to the brewery you’re standing in.
How Barley picks the next beer
The Recommendation Score
Every beer on your tap list gets a personalized score for every customer. The score is a weighted sum of seven signals — five that boost a recommendation, two that hold it back.
Personal taste match
How well the beer fits the customer's own taste graph (style, hop profile, ABV band, body, bitterness).
Similar-customer match
What customers with overlapping taste have rated highly. Collaborative filtering, scoped per-brewery for analytics, modeled cross-brewery for the customer's own profile.
Brewery popularity signal
What's currently working at this brewery. A new release that's pouring fast moves up the list.
Freshness boost
A hazy IPA released yesterday gets a freshness lift. A 60-day-old beer doesn't, unless the style ages well. Beer is perishable; the model treats it that way.
Availability boost
Beers currently on draft outrank limited bottle-shop releases for in-taproom recommendations. Barley only suggests what you can actually order.
Novelty / discovery
A small lift for beers the customer hasn't tried but their taste graph predicts they'll like — the 'safely adventurous' suggestion every regular needs.
Variety rotation
Beers Barley recently recommended rotate out for about a week, so 'what's next' isn't always 'the same one again.' A bartender doesn't keep pushing the same pour; neither does Barley.
The score itself is a number; what shows in the app is the ranked list with a plain-English reason ("You usually like juicy, soft IPAs with tropical notes"). Customers don't see math; they see "Best match: 92%."
Where customers meet Barley
One AI, three surfaces. Each surface is the right channel for a different moment.
In-taproom QR
A code on the menu opens a chat with Barley — instant recommendations based on the customer's prior visits. No app install.
On the brewery's website
An embedded chat widget that recommends beers, captures loyalty signups, and points first-time visitors at the right release.
iMessage & SMS
When a new release matches a customer's taste profile, Barley pings them on the channel they opted into — rich iMessage with release art and links on iPhone, SMS everywhere else. Segmented, not blasted.
Frequently asked questions
See Barley reason about your beer list.
Start free in minutes — connect Square and Barley starts learning your menu today. Or book a 30-minute walkthrough and we'll show you what Barley would recommend to a real customer profile from your brewery.