Create products consumers love

Empower your team with Artificial Intelligence for predictive food & beverage product development using the world's largest AI sensory data set


Why Are American Chips So Boring? International chips have all the fun logo



The AI That Knows Exactly What You Want to Eat

The Atlantic Logo



Confirming Predictive Power of AI for Foods & Beverages



Welcome to the future of product development

Predict consumer preference by modeling human sensory perception of flavor, aroma, and texture


Developing new products

Understand the flavors, aromas, and textures driving preferences for target consumer demographics in each market and identify high-preference competitive whitespace for new product development

  • Quantify flavor profiles of your products, competitor products, and new target flavor profiles 
  • Use the AI to explore millions of flavor profiles inconceivable to human formulators  
  • Set any constraints for the AI to optimize within – constrain on flavors, formulation, and preference states  
  • Screen supplier prototypes for competitive value and sustained preference over time

Entering new markets

Lift and shift successful products and flavor profiles across markets and cultures 

  • Predict which products will perform in 30+ countries around the world – and how they compare to the local competition in each market
  • Model and predict adjustments to existing products to target sustained preference of your new consumer demographics
  • Use the AI to optimize products for regional success across multi-demographic territories like the EU or SE Asia
Optimize Gear (1)

Optimizing existing products

Renovate and reformulate legacy products 

  • Automatically predict and analyze shifts in consumer preference affecting your product portfolio  
  • Optimize products with targeted attribute improvements without alienating core consumers   
  • Predict, optimize, and develop line extensions to broaden the appeal of core brands  
  • Identify areas of opportunities across flavor, texture, and aroma where your products could improve 

What our customers are saying about Gastrograph AI

Gastrograph AI is able to reduce the time to get critical consumer sensory insights and is at least an order of magnitude faster from existing empirical methods.

Gastrograph AI removes the guesswork and trial-and-error of creating new food and beverage variants by taking a data-centric approach which digitizes and systematizes this R&D process.

Our strategic partners 

Cornes Technologies

Provide Your Team With Powerful Tools to Create Market Winning Products


Gain a first-mover advantage and get to market quicker. 


Gastrograph AI's validated platform interprets and predicts flavor preferences for human beings almost everywhere. Our platform helps develop products with maximized appeal and loyalty.


Gastrograph AI saves you money by allowing you to reduce, re-use, and recycle sensory data.


The benefits of a predictive framework


Predictive Power

Once a product is profiled in Gastrograph, perception and preference predictions are automatically generated with minimal time and cost


Compound Learning

Gastrograph AI is trained on all of your data, all of the time, and is constantly learning. Models are continuously updated and made more accurate


Question Agnostic

Gastrograph AI can be continuously queried to answer new questions and “mined” for new insights


Actionable Formulation Insights

Gastrograph’s expert formulation tools help you translate consumer sensory descriptors into clear and actionable product enhancement insights

Develop products consumers love without any guesswork

Gastrograph is an ever-learning AI platform trained on the world's largest sensory data set

Unlike traditional sensory methods, Gastrograph AI can reduce, reuse, and recycle sensory data.



Gastrograph AI greatly reduces the quantity of data needed to make predictions. Standard statistical hypothesis testing requires samples size of hundreds of consumersGastrograph AI only needs a dozen observations to predict perception and preference for consumers around the world



A product or prototype only needs to be profiled once on Gastrograph AI. Standard methods require continuous re-sampling if the product wants to be used as a prototype, benchmark, product reformulation in future studies



Gastrograph AI recycles data by ”re-targeting” for a different consumer cohort to harvest new insights. By translating human perception across different demographics, we can predictively simulate the results of a CLT.

Know what your consumers want before they do

Simulate flavor, texture, and aroma models to create and test concepts. Introduce your customers to innovative flavor profiles with breakthrough products, or reimagine existing ones


Reach out to start predicting consumer preference for over 1 Billion unique consumer groups

With research in over 40 global regions and over 100 food and beverage categories, Gastrograph AI gives you deep and actionable insights into consumer types worldwide.

Customize flavor innovation by country, region, gender, age, smoking habits, taste experience, and more.

woman smiling holding coffee drink

We partnered with Ajinomoto to conduct a validation of Gastrograph AI’s predictability of consumer sensory perception and preference. A joint panel of experts from AFS and Ajinomoto designed a double-blind study.


A central location test (CLT) consumer panel was hosted in China (N = 242) to measure overall liking and 6 attribute intensity scores of 9 commercial products.


The ability to translate the perception of products across demographics with a limited number of panelists allows for the prediction of multiple new demographics at once. The accurate predictions can save a considerable amount of time compared to conducting CLT panels.


A major Asian fruit beverage company located in Japan has been experiencing a continuous decline in sales over the past year.


Our AI discovered a new beverage flavor that is preferred by the company's target market. Our AI predicted that 40% of the target demographic would give this flavor a PQ of 6 or higher.


Logoipsum increased data accuracy by 76% and decreased manual data collection time by 4 hours per week


The Past, Present, and Future of Product Development


The new approach for NPD in food and beverage is here

Read our study to learn how Gastrograph AI outperforms traditional central location testing research.


Need clarification?

How does Gastrograph work?

Gastrograph AI models people, products, and preferences. It learns how different cohorts of consumers around the world perceive flavor. It learns the flavors of individual products on the market in various countries, and it learns how to map those perceptions to those preferences. So the AI can predict for perception for different demographics, for other products anywhere in the world. 

What does predictive mean?

To have a predictive framework means you can take all the past data and make predictions without running a new experiment. The insights from a predictive framework are statistical in nature. They can have predictive layers, meaning we can predict unidentified flavors preferences and run hundreds of scenarios of predictions on simulated products. 

What problems does Gastrograph seek to solve for CPG companies?

Right now, all sensory and consumer insights are a cost center. To understand anything you're doing, you need to run more and more and more tests, and none of that has a compound ROI. You're not building value.

You're not making an asset. Using our technology and building up your branch, you're building a data asset that can be mined for future insights and reduces the amount of work you need to do in the future. So not only is it faster and more accurate, but you're able to do that at a reducing cost basis to get a positive ROI out of all the consumer, product, and market research you're doing.

How is using Gastrograph different from traditional methods?

Sensory data is slow to collect and is very expensive. When using the traditional method, the study intends to answer specific questions about a particular product, so the data collected is only used once and becomes useless. With Gastrograph, the data collected gets used for various projects and demographics; this allows you to reduce, reuse, and recycle data collection.

Where does the data come from?

We have two standing panels: one panel in New York, where people come daily to taste various products available on the market, with a child panel running once a week. The second standing panel we have is in Shanghai. 

We also have a team that travels worldwide to collect data on the markets. So far, we can model sensory perception and preference in over 30 countries, and we are continuously expanding.

Develop products consumers love without any guesswork