Morrisons has introduced a generative AI-powered tool, supported by Google Cloud and Gemini, which assists customers in locating products within their stores.
This innovation is part of the supermarket's continuous digital transformation and data infrastructure revamp, as disclosed by .
The feature enables shoppers to input queries for items, from 'tahini' to 'that tomato puree in a tube', delivering real-time product locations at the aisle level.
READ MORE: {}
The tool has already handled over 50,000 daily searches during peak times.
"We've used Google's foundational models, but we've built the application and the way we use the models completely internally", Peter Laflin, Morrisons' director of data, shared with City AM.
While the system utilises Google Cloud's Vertex AI platform and Gemini large language models (LLMs), it was crafted by Morrisons' own data science team.
Laflin emphasised that this approach was taken intentionally amid growing concerns about third-party vulnerabilities.
"We're in control of it, and that has huge advantages. We're able to build for scale, so if it's Christmas or Easter and usage jumps, the system responds," he explained.
Sector shifts and cyber threats
Most Read
This development occurs as 海角视频 grocers are rapidly adopting AI to enhance efficiency and generate media revenue.
Sainsbury's is on the verge of launching its proprietary media platform 'Pollen', which leverages AI to fine-tune advertising campaigns using Nectar data.
In parallel, US giant Walmart has also made significant investments in comparable technologies.
Amidst the wave of innovation, there is an escalating threat from cyber risks. In June, Marks & Spencer disclosed that some customer account data had been compromised due to a breach at a third-party service provider.
Morrisons was also impacted by a ransomware attack on its logistics partner, Blue Yonder, last year.
Laflin emphasised the importance of internal development and secure in-house hosting for their tool, stating: "We can be confident that our data is secure, it's always at the forefront of what we do."
Where can I find...
In a conversation with City AM, Laflin explained that the inspiration for the product search tool stemmed from a frequent and straightforward customer query.
Don’t miss
"The most common question that our colleagues in store get is: 'Where can I find X?' So if we can help customers answer that themselves through the app, that's a win for them - and for our colleagues too," he asserted.
He mentioned that the team concentrated on resolving everyday issues, such as locating niche items that are not always easy to find or clearly marked in stores.
"Tahini is a good example", he noted. "It's something specific, that's small, and can be difficult to find."
The system has been trained to accommodate spelling mistakes, brand names, and vague terms, aiming to provide the best matches based on each store's unique layout and stock levels.
Laflin also highlighted that the system was built to handle increased demand during peak seasonal periods.