Source proof for adidas turns customer reviews into insight at scale with GenAI

adidas turns customer reviews into insight at scale with GenAI | Databricks Skip to main content Login Why Databricks Discover For App Develop…

…ore efficient prompt engineering. What data did adidas’ GenAI solution analyze? The solution analyzed more than 2 million customer product reviews, using retrieval augmented generation (RAG) to surface sentiment and actionable insights at scale. Can adidas’ GenAI infrastructure support use cases beyond product reviews? Yes.…

…cations in customer service, knowledge management and other feedback channels.” By integrating Databricks technologies like Databricks AI Search, Unity Catalog, Model Serving and MLflow, adidas created a global-scale solution that is fast, governed and extensible. It not only supports the company’s goal, but also sets the stage for a more per…

…2 million reviews for deeper feedback analysis The results were transformative. Latency dropped by 60%, cutting average response time from 15.5 seconds to six. More efficient prompt engineering and smaller context windows reduced token input size by 98.5%, from 200,000 to just 3,000 tokens per query. These optimizations lowered compute costs by over 90%. Through GenAI, adidas improved review analysis efficiency by up to 30–40%, cutting down extensive manual workloads across global teams. The intuitive chatbot enabled faster decision-making across teams, from design…

…rity and Trust Ready to get started? Get a Demo Login Contact Us Try Databricks Customer Stories / Adidas CUSTOMER STORY Driving product innovation through customer feedback adidas turn…

…tency reduction, putting action insights into the hands of product teams faster adidas, the iconic German sports brand, has a legacy of innovation — from pioneering screw-in studs that revolutionize…

…vice, knowledge management and other feedback channels. Share this post Details Industry : Marketing , Retail and Consumer Goods Use Case : Data Science , Data Engineering Cloud : AWS Product : Agent Bricks ,…

…l time, ensuring teams could act quickly on what customers actually wanted. But adidas’ existing infrastructure couldn’t support that vision. Their legacy chatbot wasn’t built on GenAI or RAG, leading to generic answers, high compute costs and frustrating 15-second response times. Meanwhile, review analysis remained largely manual, which was time-consuming, and nontechnical users struggled to access insights. “With query payloads exceeding 200,000 tokens, we were overloading our back-end…

…which was time-consuming, and nontechnical users struggled to access insights. “With query payloads exceeding 200,000 tokens, we were overloading our back-end systems and limiting adoption,” Rahul Pandey, Senior Solutions Architect at adidas, said. Building a scalable…

…das began their transformation by preparing a robust data layer to support RAG. First, over 2 million product reviews were embedded using models like Databricks BGE Large, optimized for semantic search. These vectorized reviews captured the context of customer feedback, not just ke…

…ectorized reviews captured the context of customer feedback, not just keywords. The embeddings were then indexed using Databricks AI Search, Databricks’ native solution for fast, meaning-based retrieval. With the vector database in place, adidas deployed a RAG pipeline using Model S…

…solution for fast, meaning-based retrieval. With the vector database in place, adidas deployed a RAG pipeline using Model Serving. The pipeline retrieved relevant review snippets, combined them with user prompts and generated responses using LLMs such as Claude Haiku. Unity Catalog ensured secure access and governance of models and data, while su…

…them with user prompts and generated responses using LLMs such as Claude Haiku. Unity Catalog ensured secure access and governance of models and data, while supporting components like APIs and the chatbot interface were hosted in…

…interact with the tool. To manage experiments and maintain system reliability, adidas used MLflow to track model performance and iterate efficiently. Feedback loops and error tracking ensured the chatbot stayed aligned with evolv…

…2 million reviews for deeper feedback analysis The results were transformative. Latency dropped by 60%, cutting average response time from 15.5 seconds to six. More efficient prompt engineering and smaller context windows reduced token input size by 98.5%, from 200,000 to just 3,000 tokens per query. These optimizations lowered compute costs by over 90%. Through GenAI, adidas improved review analysis efficiency by up to 30–40%, cutting down extensive manual workloads across global teams. The intuitive chatbot enabled faster decision-making across teams, from design…

…GenAI 30–40% Improvement in analyst efficiency in review-based decision-making 91.67% Cost savings by transitioning to more efficient LLMs 60% Latency reduction, putting action insights into the hands of product teams…

…luding nontechnical users, to improve product development and brand experience. A RAG chatbot would automate review analysis and deliver context-rich responses in real time, ensuring teams could act quickly on what customers actually wanted. But adidas’ existing infrastructure couldn’t support that vision. Their legacy…

…ver customer sentiment. That’s why the brand partnered with Databricks to build a scalable GenAI solution powered by retrieval augmented generation (RAG) — unlocking 30–40% efficiency gains for analysts by transforming over 2 million…

…ipeline retrieved relevant review snippets, combined them with user prompts and generated responses using LLMs such as Claude Haiku. Unity Catalog ensured secure access and governance of models and data, while s…

…luding nontechnical users, to improve product development and brand experience. A RAG chatbot would automate review analysis and deliver context-rich responses in real time, ensuring teams could act quickly on what customers actually wanted. But adidas…

…ectorized reviews captured the context of customer feedback, not just keywords. The embeddings were then indexed using Databricks AI Search, Databricks’ native solution for fast, meaning-based retrieval. With the vector database in place, adidas deployed a RAG pipeline using Model S…

…solution for fast, meaning-based retrieval. With the vector database in place, adidas deployed a RAG pipeline using Model Serving. The pipeline retrieved relevant review snippets, combined them with user prompt…

…them with user prompts and generated responses using LLMs such as Claude Haiku. Unity Catalog ensured secure access and governance of models and data, while supporting components like APIs and the chatbot interface were hosted in…

…interact with the tool. To manage experiments and maintain system reliability, adidas used MLflow to track model performance and iterate efficiently. Feedback loops and error tracking ensured the chatbot stayed aligned with evolv…

…das began their transformation by preparing a robust data layer to support RAG. First, over 2 million product reviews were embedded using models like Databricks BGE Large, optimized for semantic search. These vectorized reviews captured the context of customer feedback, not just ke…

…ipeline retrieved relevant review snippets, combined them with user prompts and generated responses using LLMs such as Claude Haiku. Unity Catalog ensured secure access and governance of models and data, while s…

…etail and Consumer Goods Use Case : Data Science , Data Engineering Cloud : AWS Product : Agent Bricks , Delta Lake , Unity Catalog Ready to get started? Try Databricks for free Learn more about our product Talk…

…arketing , Retail and Consumer Goods Use Case : Data Science , Data Engineering Cloud : AWS Product : Agent Bricks , Delta Lake , Unity Catalog Ready to get started? Try D…

…arketing , Retail and Consumer Goods Use Case : Data Science , Data Engineering Cloud : AWS Product : Agent Bricks , Delta Lake , Unity Catalog Ready to get started? Try D…