A HoReCa platform that brings AI into the kitchen.

Growzer connects hospitality companies, wholesalers and manufacturers on a cloud platform we've built and run since 2016.

Growzer, Belgium · 2016 – ongoing
  • Applied AI
  • AI Engineering
  • Software Engineering

70% auto-completed

AI fills in recipe data from dish names, descriptions and photos

200+ demand signals

Weather, events and holidays drive daily forecasts per outlet and SKU

FoodEx2 product taxonomy

Every wholesaler’s products mapped to one standard, without duplicates

Growzer AI-generated menu item with ingredient matching Growzer purchasing overview dashboard with anomalies and insights
Applied AI

Recipe Generation from Dish Photos

Chefs see digitizing recipes as tedious and low-value, so onboarding relies on manual work by the sales team and menu data stays incomplete. Growzer’s sales team handled this by hand during onboarding, which slowed the process and limited data completeness.

Up to 70%

Of the required recipe information is auto-completed in the menu engineering module, straight from a dish photo or name.

Faster onboarding

Recipes no longer wait for the sales team to type them in, so newly signed restaurants start using Growzer sooner.

Minor edits only

The AI drafts every recipe, leaving only minor adjustments for the chef or the onboarding team to review and confirm.

What we did

Vision AI and NLP interpret dish photos, names and descriptions to draft structured recipes, auto-completing up to 70% of the required information.

An AI assistant embedded in the Growzer onboarding flow combines image recognition with language understanding and proposes each structured recipe directly inside the menu engineering module, ready for the chef to review.

How it works
  1. Chef uploads a dish photo during Growzer onboarding
  2. Vision AI labels the image and identifies the dish’s ingredients and structure
  3. NLP parses the dish name and description to infer likely ingredients, cooking methods and portion sizes
  4. The AI assistant proposes a structured recipe draft in the menu engineering module
  5. The chef or onboarding team makes minor adjustments and confirms
Key capabilities

Image-based recipe generation

Vision AI labels a dish photo and identifies its ingredients and structure, turning the image into a recipe draft automatically.

Dish name interpretation

NLP reads dish names and descriptions to infer the likely ingredients, cooking methods and portion sizes behind every dish.

Trained on chef data

Prototyped on annotated chef datasets, tuned with structured human feedback and iterated with the onboarding team in the Growzer beta.

Technology
  • Vision AI
  • Image labeling & dish recognition
  • Natural language processing (NLP)
  • AI assistant
Impact

Turning menu data into business value

Complete data from day one

Restaurants start on Growzer with recipe data that is complete from day one, so menu and cost tools work immediately.

Less reliance on chefs

Menu digitization no longer depends on chefs’ willingness to type up recipes, a task they find time-consuming and low-value.

Better menu data

Structured AI drafts replace incomplete manual entries, raising the overall quality of menu data across the Growzer platform.

Profitability per dish

Complete recipes lay the groundwork for profitability analysis per dish, showing which menu items truly earn their place.

Dynamic menus ahead

The structured recipe base enables future dynamic menu optimization, so menus can adapt as costs and demand change over time.

Testimonial
Working with Wildstream is, overall, just a pleasant experience. Quality people, quality processes, quality products, quality advice. Every moment spent with them, about work or just casual conversation, is quality time.
Frank De Meulder, CEO Growzer

Bring us a challenge like this

Growzer started as one operating problem and became a platform. Tell us where your ordering, forecasting, product data or menu performance is holding the business back, and we will tell you where AI is worth building first.