ChatGPT Plugin

Butterfly

Talk To Your Restaurant

Brand: Butterfly

Category: Commerce
Primary Subcategory: Restaurant & Coffee Brand Ordering

Integration details

Description

Talk to your menu like you talk to your team. With Butterfly in ChatGPT, you can check what guests are viewing, see which dishes are getting attention, track scans and orders, and understand what is working. You can also update prices, manage opening hours, create promotions, control offer-wheel discounts, and translate dishes—all through a simple conversation.

Integration type: Plugin
Verification status: Not applicable
Platform: ChatGPT
Category: Commerce
Primary Subcategory: Restaurant & Coffee Brand Ordering
Secondary Subcategories: None listed
Brand: Butterfly
Access: Account required
First tracked: 2026-07-29
Tool count: 18
Market: US

Agent DiscoverabilityChatGPT Plugin Discovery Score

ChatGPT organic discovery is live

Your score is coming

ChatGPT now suggests Plugins on its own when they match a user's request.Your Plugin Discovery Score measures how often yours appears, and it will show here as soon as it’s ready.

Sign up to track your Plugin See who ChatGPT suggests

ChatGPT recommends Airtable when a user asks it to update a CRM. — ChatGPT surfaces Airtable because it matches the user's request.

Primary Subcategory

Competing in ChatGPT Restaurant & Coffee Brand Ordering

View Category

Listed in alphabetical order

Primary Subcategory

% Arabica UAEComing soonGet notified

20TabsComing soonGet notified

24TechDesignComing soonGet notified

AtlasComing soonGet notified

Buffalo Wild WingsComing soonGet notified

ButterflyComing soonGet notified

Tools

18 tools agents can invoke

Apply hours after user confirmed preview_hours. Pass confirm_token.
Apply bulk menu changes ONLY after user confirmed preview_menu_bulk. Pass the confirm_token from that preview.
Apply offer wheel settings after user confirmed preview_offer_wheel.
Apply promotion change after user confirmed preview_promotions.
Apply translations after user confirmed preview_translations.
Read-only AR open rates and AR-assisted dish performance.
Read-only per-dish views, AR opens, and order proxies.
Read-only menu snapshot. Each item has item_id (same as id) and price_aed. Always call this before preview_menu_bulk so you use real item_id values.
Read-only offer wheel config and 30-day spin stats.
Read-only recent orders and top ordered items.
Read-only restaurant overview: scans, clicks, AR opens, orders for a date range. Associations only, not causation.
Read-only plan caps so proposals stay within limits.
Read-only list of promotions and their settings.
Preview business hours change. Confirm with user before apply_hours.
Preview bulk menu create/update/delete. Prefer item_id from get_menu (id also accepted). price or price_aed accepted. Dish name alone is OK for a unique match. Show the returned diff table; only call apply_menu_bulk after the user confirms.
Preview offer wheel settings (not outcomes). Requires menu_id. Confirm before apply_offer_wheel.
Preview promotion create/update/pause. Include menu_id from get_menu. Confirm before apply_promotions.
Preview dish i18n translations. Prefer item_id from get_menu (id accepted). Confirm before apply_translations.

FAQs

Butterfly ChatGPT Plugin FAQ

How the directory, categories and Discoverability Score work.

Read the methodology

How do I improve Butterfly's ChatGPT Plugin discoverability?

The levers are the listing surface agents actually read: names, descriptions, keywords, tool metadata, and registry health. Which lever matters depends on where discovery breaks, which is what continuous measurement shows.

What are Butterfly alternatives on ChatGPT?

As of 2026-10-29, Butterfly competes with % Arabica UAE, 20Tabs, 24TechDesign, Atlas, Buffalo Wild Wings, Convious, HappyCake, Little Caesars Concierge and 8 more in ChatGPT Restaurant & Coffee Brand Ordering, ranked by public Discoverability Score.

Where is this profile measured?

This profile uses the geography attached to the latest public registry snapshot: US. Locale tags are intentionally omitted.