The foodservice industry faces major labor, quality control and sustainability challenges that are exacerbated by the pandemic. According to according to NSF International, a product testing and certification organization, more than half of quick-service restaurant (QSR) managers found employee turnover to be a problem for their company, with 20% saying it had the greatest negative impact on the past. activities number of months. One in 10 managers and employees at NSF admitted in a February survey that due to high order volumes, they recently skipped automatic cleaning cycles or ignored error messages on equipment.
Ingo Stork-Wersborg claims his company, PreciTaste, has the solution – with AI as the main ingredient. PreciTaste sells a service that monitors food quality in fast-serve kitchens and forecasts supply and demand to make recommendations for preparing orders to employees.
PreciTaste was launched until today, marking the close of the startup’s $24 million Series A round. Melitas Ventures and Cleveland Avenue LLC led the tranche along with participation from investors including the CEOs 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 optimization in the QSR space. While other industries are experiencing a slowdown, food service operators continue to increase their focus on digital solutions to create kitchen efficiencies, which is a key factor in securing our… funding,” Stork-Wersborg told londonbusinessblog.com. “For a QSR operator, PreciTaste is an established platform for accurate, demand-driven cooking. It maximizes efficiency, improves quality and reduces food waste through its own ‘always-on’ kitchen management system. The technology has been proven to reduce overheads and food waste by instructing crews to cook only as much as they need and is highly scalable.”
Stork-Wersborg co-founded PreciTaste with his wife Laura more than a decade ago, building on technology originally developed at the Technical University of Munich. The company started out as PreciBake and focused on automating baking processes in commercial ovens.
PreciTaste’s current flagship is designed to handle a wider range of tasks, such as how many burgers to cook for a lunch rush. First, the system predicts demand by monitoring store traffic (via cameras), POS systems and available inventory. It then uses additional cameras in the kitchen to monitor the stock and determine the amount of food to be cooked.
Suggestions (eg ‘grill two burgers’, ‘bake bread for 40 minutes at 375 degrees’) are passed on to the crew via touchscreens. They will also see alerts if orders are inaccurate, depending on whether a QSR operator decides to enable the feature. Managers can remotely monitor the activities of one or more restaurants at the back.
Stork-Wersborg says PreciTaste can eliminate a significant portion — 85% — of food waste at the point of sale, a claim that is likely to pique the interest of potential restaurant customers. Driven by inflation, prices for quick meals rose 7.3% in May, forcing diners to cut back on their spending. a recent questionnaire found that 54% of consumers in the US eat out less often, while 33% choose to “trade in” in their restaurant selection.
But AI systems are only as accurate as the data used to train them. Unfortunately, Stork-Wersborg declined to say which samples were used to train PreciTaste’s algorithms, nor whether the system performs equally well in different food types and kitchen setups.
“PreciTaste uses proprietary data augmentation [machine] learning methods based on the foodservice’s vast, rapidly growing data library, which adds image data from the 19,000 meals prepared every five minutes that we currently track, to provide our customers with computer vision that works at scale and across multiple geographies,” Stork- Wersborg said. “To make its computer vision work in any kitchen, including unfamiliar environments or situations, PreciTaste uses its simulation data for growing food operations in its machine learning pipeline to increase robustness, which includes data of varying levels of oiliness, aspect ratios, kitchen tools (including gloves, etc.) ), occlusions and more.”
When asked about another hot-button topic – privacy – Stork-Wersborg said camera data is deleted “in most cases” right away. A PreciTaste competitor, Agot AI, has been described not very flattering by some publications as a “supervision” clothing.
“PreciTaste provides an offline-first edge AI solution. As such, we have full control over what happens to customers’ data and can respond to their data protection needs and data retention policies,” said Stork-Wersborg. “Because our model training and optimization require computing resources that are not available at the edge, some data is anonymized and uploaded to our servers. Most data is analyzed at the edge and in most cases deleted immediately.”
Stork-Wersborg says PreciTaste’s prep monitoring system is now installed at more than 1,500 locations, including a “growing number” of fast casual restaurants in the US. (He wouldn’t name any brands.) But the company could face a tough road to future growth, given competition from Dragontail Systems, Leanpath, Winnow, Miso Robotics, and the aforementioned Agot.
Stork-Wersborg argued that technological superiority is the difference maker of PreciTaste.
“The system collects data that not only helps the restaurants operate more efficiently, but also allows management to verify that operating procedures are followed even when management is not on site. As such, it removes a blind spot and provides top-level management figures that were previously unavailable 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 in Germany, India and the US and plans to hire more than 25 employees by the end of the year.