LAS VEGAS — When Schnuck Markets launched its AI-powered agentic shopping assistant earlier this year, the first question shoppers asked wasn't about dinner recipes — it was what time the stores open.

The Midwestern grocer's technology teams had built the tool largely to help online shoppers solve the nightly conundrum of what to eat, said Caleb Carr, the grocer's senior director of data science and engineering.

"That was our premise: What can we really do to support and answer that question for our customers?" Carr said Tuesday, Sept. 22, during an educational session at Groceryshop in Las Vegas.

The early flub underscored the importance of backing AI tools with comprehensive, high-quality data that goes beyond recipes and product ingredients, Carr said. Grocers sit on reams of information — from nutrition details to custom cake pricing — but typically store it across multiple disconnected systems.

"It is one of the few industries that have so many disjointed data sources, and so a lot of the work to build a successful AI agent or even just be discoverable is making sure we have that data available," said Carr.

Product-level data gaps present a persistent problem. Although 90% of Schnucks' SKUs carry syndicated data — information formatted and regularly updated for the retailer — that coverage didn't always answer health-related queries.

"One of the [inputs] we're seeing a lot from our customers is, 'I want a meal that has this many calories per serving.' Well, if you don't have calories for ingredients … you can't answer that question," said Carr.

Getting cohesive, up-to-date data from small producers that lack access to syndication tools has also proven challenging, Carr noted.

Schnucks is also working to feed internal data and institutional knowledge into the system. Skilled bakery and meat department staff often hold key information that exists nowhere in writing. Customers have already asked the assistant to recommend a birthday cake message, Carr said.

"We have a great cake program, but how do we take the awesome expert knowledge of our bakers and our bakery team and turn that into something that can serve our customers 24/7?" said Carr.

Internal jargon posed another obstacle. Schnucks, like many retailers, calls its discounts TPRs — temporary price reductions — a term shoppers don't understand. The grocer built an AI model to translate.

"We've actually got a model that our primary agent reaches out to that helps decode and put it into less business speak," said Carr.

So far, Schnucks is pleased with shoppers' uptake of the assistant and optimistic about its ability to evolve and deepen customer relationships. Although other AI platforms and tech providers have launched their own agentic grocery shopping tools, Carr argues grocers themselves are best positioned to build assistants reflecting their food expertise and their shoppers' preferences.

"As grocers, we need to make sure that we own that relationship and we're able to connect," he said.