Lowe’s answers millions of home improvement questions with OpenAI

Built with OpenAI, Mylow and Mylow Companion, Lowe’s AI assistants for customers and store associates, have helped Lowe’s answer millions of questions from customers and associates since launch in Spring 2025. Those questions start with a project, whether a customer is planning a room to paint or an associate is helping with an unexpected repair.

“When you’re buying a t-shirt and it doesn’t fit, you just return it. No big deal,” says Seemantini Godbole, Executive Vice President, Chief Information and AI Officer at Lowe’s. “But if you’re renovating a kitchen or redoing your floors, those are expensive decisions. You want to feel confident. And that requires expertise.”

Lowe’s Red Vest associates have long helped customers navigate that complexity. But with stores up to 130,000 square feet and tens of thousands of SKUs, even seasoned team members cannot know everything, especially when a question falls outside their department or experience. Online shoppers face a similar challenge because traditional search tools and website experiences only help if they already know what to look for.

Lowe’s saw an opportunity to put project expertise closer to the people making decisions, whether a customer was starting online or an associate was helping in the aisle. That required AI that could understand natural-language project questions, reason across the details of a home improvement job, and respond conversationally. It also needed to work by voice for associates on the move and perform reliably across customer and associate experiences at Lowe’s scale. OpenAI’s models gave Lowe’s those capabilities.

“We’ve been really intentional,” says Godbole. “We didn’t want to just update our systems. We wanted to rewire the entire business to support projects, not just products.”

Lowe’s had already been investing in AI for years. What changed in 2023 was customer behavior.

“ChatGPT changed expectations,” says Joe Cano, SVP of Digital Commerce. “Customers now expect fast, expert answers 24/7. They want to describe their project in natural language and get help, not open ten tabs to figure out what mulch works in their zip code.”

Lowe’s uses OpenAI models to power two experiences that support home improvement projects.

• Mylow Companion gives associates conversational answers across departments, bringing project know-how into stores with access on mobile and desktop.

• Consumer-facing Mylow is a conversational advisor on Lowes.com that helps customers ask open-ended questions and get step-by-step guidance, product recommendations, and relevant how-to content.

Mylow Companion brings frontier intelligence to every associate by putting project guidance at their fingertips. Nearly half of Mylow Companion interactions happen through voice. Associates can describe a customer’s question in their own words, and OpenAI models help turn it into guidance grounded in Lowe’s project knowledge. That puts answers within reach while associates stay focused on the person in front of them.

The associate listens to what the customer needs and uses their judgment to put the guidance to work.

In the paint aisle, an associate might ask Mylow Companion, “A customer is painting their living room and wants a finish that’s easy to clean. What should I recommend?” The associate can ask aloud and use the guidance to talk through options with the customer, without stepping away.

“Before, if a customer needed to replace a hose bib and the plumbing expert wasn’t there, you’d have three people spending 30 minutes trying to help. Now, one associate can get it done in minutes,” says Que Vance, EVP of Stores at Lowe’s.

Mylow Companion is available to roughly 300,000 associates across 1,700 stores in all 50 states. Mylow Companion expands the help both new and experienced associates can offer. Internal usage patterns suggest newer associates turn to it frequently, while experienced associates use it to answer customer questions beyond their usual departments.

Mylow brings the same project-first approach for its customers on Lowes.com. Built on OpenAI models, it gives customers a conversational way to plan projects online. Instead of navigating product categories or searching with the exact right keywords, customers can describe exactly what they are trying to do and get step-by-step guidance, product recommendations, and relevant how-to content.

“What makes Mylow powerful is it understands intent,” says Cano. “Most people don’t come to our site with a product in mind. They come with a problem. ‘I want to hang shelves,’ or ‘I need paint that holds up to my three kids.’ The tool figures out what they mean, and helps them finish the job.”

Mylow users convert at three times the rate of online shoppers who do not use Mylow, according to Lowe’s Q2 2026 earnings call.

“What if each associate asked just one question a day? That’s 300,000 questions. That’s how we measure success now,” says Godbole.

That question captures how Lowe’s thinks about adoption in stores. Separately, Mylow and Mylow Companion have answered millions of questions since launch. OpenAI models help Lowe’s turn those everyday questions into project guidance customers and associates can use right away.

When associates use Mylow Companion to help shoppers in the aisle, Lowe’s has seen customer satisfaction increase by 200 basis points. For Lowe’s, that is Intelligence at Work. Project expertise is easier to reach, whether a customer is planning online or an associate is helping face-to-face.

Lowe’s has expanded Mylow Companion to support natural voice interaction and adopted ChatGPT Enterprise for its Store Support Center, extending its use of OpenAI beyond the store aisle. Lowe’s is continuing to bring Intelligence at Work with OpenAI through voice and model capabilities that make it easier for customers and associates to get help—so shoppers can find the right products, make confident decisions, and move their projects forward.

“Mylow Companion builds on the judgment and experience of our Red Vests, helping them stay with the customer and turn a complex question into a clear next step. We’re in the business of fixing problems and fulfilling dreams,” says Godbole. “With the right tools, we can do that better than ever before.”