Lowe's
conversational genAI shopping advisor plus associate copilot
Launched in 2025 with OpenAI, Lowe's Mylow genAI advisor and its associate copilot Mylow Companion, deployed to all associates across more than 1,700 stores, together handle about 1 million questions per month.
Objective
Give every customer expert project advice on lowes.com and give every in-store associate the equivalent of an expert colleague, to remove decision friction on technical projects and convert more.
The deployment
Mylow is Lowe's conversational shopping advisor, launched in March 2025 on lowes.com and mobile web, developed with OpenAI. The customer asks open questions about their project and receives step-by-step advice, product recommendations, and links to how-to articles and videos. In May 2025, Lowe's deployed Mylow Companion to all associates across its more than 1,700 stores, on the terminals they already use. The associate queries the assistant in natural language, including by voice, on product details, installation advice, or stock. According to Retail Dive, Mylow and Mylow Companion together handle about 1 million questions per month. A Spanish version of Mylow Companion was added in February 2026.
Results Proof C
Deployment and usage figures released by Lowe's in its official press releases (1,700 stores, all associates) and picked up by major retail press (Retail Dive, CX Dive), which names the brand and the volume of a million questions per month. No isolated financial result published on the tool, which caps it at C despite concordant sources.
How it works
Documented architectureThe stack in detail
- llm Modeles generatifs OpenAI conversational backbone of Mylow and Mylow Companion, developed in partnership with OpenAI; model version not published
- outil Mylow conversational shopping advisor on lowes.com and mobile web: step-by-step project advice, product recommendations, how-to links
- outil Mylow Companion associate copilot deployed on the existing terminals of the more than 1,700 stores, queryable by text and voice, Spanish version added in 2026
- infra Couche RAG maison Lowe's project knowledge base, product catalog and local stock exposed to the agent in real time
How it runs, concretely
For ops teams-
1Project question customer or associate
The customer on lowes.com or the associate in store asks a question in natural language, by text or voice.
-
2Understanding and retrieval AI
The LLM interprets the request and fetches project advice, product sheets and stock from the Lowe's knowledge base.
-
3Guided answer AI
The assistant returns step-by-step advice, products and how-to links, and on the store side serves the associate speaking to the customer.
-
4Follow-up and adaptation data team
The teams measure volume, satisfaction and adoption, and adjust the knowledge and journeys by segment (consumer, pro).
The quality of project answers and the availability of local stock. If the product reference data and inventory are not up to date, the assistant steers toward the wrong products or out-of-stock items.
How your customers perceive this type of use
Sourced studiesLes consommateurs n'acceptent pas les chatbots par defaut : 64% prefereraient que les entreprises n'utilisent pas d'IA dans leur service client (Gartner, 2024) et pres d'un utilisateur sur cinq du service client par IA n'en retire aucun benefice (Qualtrics, 2025). L'acceptation se construit sur trois conditions mesurees par Salesforce : savoir qu'on parle a une IA, pouvoir escalader vers un humain, comprendre la logique de l'agent.
Acceptance conditions
- Etre informe qu'on parle a une IA et non a un humain (pres de 75% le demandent, Salesforce 2024)
- Un chemin d'escalade clair vers un agent humain (45% plus enclins a utiliser l'agent IA, Salesforce 2024)
- Une logique de l'agent clairement expliquee (44% plus enclins, Salesforce 2024)
Red lines
- Rendre l'humain injoignable : c'est la premiere inquietude des consommateurs sur l'IA dans le service client (Gartner 2024) et 50% craignent que l'IA les coupe du contact humain (Qualtrics 2025)
- Remplacer le service client par l'IA sans alternative : 53% envisageraient de partir chez un concurrent (Gartner 2024)
Sources: Salesforce 2024 · Gartner 2024 · Qualtrics 2025
How to replicate
Inference, not sourcedData prerequisites
- Structured project and how-to knowledge base
- Product catalog and local stock exposed in real time
- Session history to measure satisfaction and conversion
Org prerequisites
- AI transparency rule toward the customer
- Associate devices able to carry the copilot in store
- Adoption and satisfaction measurement loop
Possible stack
- Generative LLM via API
- RAG layer over project knowledge and catalog
- Voice interface for field use
The plan, step by step
- Step 1Index project knowledge, catalog and local stock for RAGDeliverable: Queryable base with verified stock freshness
- Step 2Build the web advisor on a high-traffic technical category, with guardrails and AI transparencyDeliverable: Agent in beta, correct-answer rate evaluated on real questions
- Step 3Launch on the site and measure volume, satisfaction and effect on project conversionDeliverable: Agent in production + usage dashboard
- Step 4Bring the copilot onto associate terminals, including the voice interface, in a pilot on a subset of storesDeliverable: Store pilot with measured associate adoption
- Step 5Deploy to the full network and localize by segment and languageDeliverable: Full rollout + versions by segment (consumer, pro) and by language
First step: Index project knowledge and the catalog for RAG, launch a web advisor on a high-traffic technical category, then extend to associates.
The same pattern, proven in other industries
Booking.com
genAI trip planning assistant
Burberry
genAI copilot for consultants (search, image recognition, complete-the-look)
Homes.com
natural-language voice and text search, then conversational assistant
Sources
- S1 How Lowe's tailors its AI-backed Mylow to different customers Established press archive pending
- S2 Lowe's deploys first at-scale AI assistant for retail associates Primary archive pending
- S3 Lowe's Launches First AI-Powered Home Improvement Virtual Advisor Primary archive pending
- S4 Lowe's credits associate-facing app for customer satisfaction boost Established press archive pending
An error, newer info, a source?
This page lives on its accuracy. If a figure has moved, if the deployment has changed, or if you have a higher-quality source, tell us. Every sourced correction is verified before publication.