The food service industry is facing tough labor, quality control and sustainability challenges exacerbated by the pandemic. According to NSF International, a product testing and certification organization, more than half of quick service restaurant (QSR) managers see employee turnover as an issue in their business, with 20% saying said it had a negative impact on domestic operations in the past few months. One in 10 managers and employees admitted to an NSF survey in February that, in the face of high standards, they have recently skipped automatic cleaning cycles or ignored wrong messages on equipment.
Ingo Stork-Wersborg claims his company, PreciTaste, has the solution – with the key ingredient being AI. PreciTaste sells a service that monitors food quality in quick service kitchens, by forecasting demand and supply to regulate staff preparation recommendations.
PreciTaste closed as of today, marking the closing of the startup’s $24 million Series A round. Melitas Ventures and Cleveland Avenue LLC are co-leading the round of participation from investors, including the executives of Burger King and McDonald’s and Enlightened Hospitality Investments, the fund co-founded by Shake Shack CEO Danny Meyer.
The pandemic has increased the need for digital improvements in the QSR space. While other industries are experiencing a downturn, food service operators continue to strengthen their focus on digital solutions to create efficiencies in the kitchen, which is a major factor in securing our… investment,” Stork-Wersborg told TechCrunch. .” A QSR operator, PreciTaste is a platform dedicated to precision, on-demand cooking. It increases efficiency, enhances quality and reduces food waste through its ‘always on’ kitchen management system. The technology has been proven to reduce overhead costs and food waste by instructing employees to cook only what they need and is highly scalable.”
Stork-Wersborg co-founded PreciTaste ten years ago with his wife, Laura, building on technology originally developed at the Technical University of Munich. The company started as PreciBake, focusing on automating baking processes in commercial ovens.
The current PreciTaste brand is designed to handle various tasks, such as how many burgers to prepare before the lunch rush. First, the system predicts demand by monitoring store traffic (via cameras), point-of-sale systems and available materials. It then uses additional cameras in the kitchen to check supplies and determine the amount of food to be cooked.
Prompts (eg, “bake two burgers,” “bake a bun for 40 minutes at 375 degrees”) are relayed to employees via touch screens. They will also see warnings if the orders are not valid, depending on whether the QSR operator decides to enable the feature. Managers can monitor the operations of one or more restaurants remotely from the backend.
Stork-Wersborg says PreciTaste can eliminate a significant amount – 85% – of food waste at the point of sale, a claim that is likely to pique the interest of restaurant customers. Driven by inflation, fast food prices rose 7.3% in May, prompting diners to cut back on spending. One recent survey found that 54% of consumers in the United States eat out less often and 33% choose to “downsize” their restaurant selections.
But AI systems are exactly how data is used to train them. Unfortunately, Stork-Wersborg refused to say which samples were used to train the PreciTaste algorithms, as well as whether the system handles different types of food and cuisine equally.
“PreciTaste uses proprietary [machine] learning methods based on a large, rapidly growing library of food service data, which incorporates data from the 19,000 images of meals prepared every five minutes that we currently monitor, to provide our customers with computer vision that works at multiple sizes and regions,” said Stork-Wersborg. “To make its computer vision work in any kitchen, including in unknown environments or conditions, PreciTaste uses simulation data. its growing food operations in the machine learning pipeline to increase robustness, which includes data on different levels of fat, aspect ratio, kitchen equipment (including gloves), hidden areas and more.”
When asked about another hot topic – privacy – Stork-Wersborg said that camera data “in most cases” is deleted immediately. PreciTaste’s competitor, Agot AI, has been unfavorably described in some publications as a “protective” outfit.
“PreciTaste offers the first edge of AI online. In this way, we can fully control what happens to customers’ data and meet their data protection needs and data retention policies,” said Stork-Wersborg. “Since our model training and optimization requires computational resources that are not available at the edge, some data is encrypted and uploaded to our servers. Most of the data is analyzed at the edge and, in most cases, immediately deleted.”
Stork-Wersborg says PreciTaste’s preparation monitoring system is now installed in more than 1,500 locations, including a “growing” list of U.S.-based casual restaurants. (I won’t name names.) But the company could face a tough path to future growth, given the competition from the likes of Dragontail Systems, Leanpath, Winnow, Miso Robotics and Agot we mentioned above.
Stork-Wersborg argues that technological superiority is the PreciTaste’s differentiator.
“The system collects data that not only helps the restaurants to work efficiently, but also enables management to ensure that the operating procedures are followed, even if management is not on site. In this way, it It removes blind spots and gives senior management previously unavailable numbers to base their decisions on,” said Stork-Wersborg. “PreciTaste offers an AI kitchen management solution that combines advanced computer vision and deep learning.”
PreciTaste employs 98 people across Germany, India and the US and plans to hire more than 25 employees by the end of the year.