Enterprise Knowledge Search · Marketing Personalization
adidas needed a more scalable review-analysis stack because its legacy chatbot was not built for GenAI or RAG, response times were high, and nontechnical users could not easily explore customer sentiment.
Reported impact
adidas reported Driving product innovation through customer feedback 30–40% efficiency gains, Analysts transformed over 2 million customer reviews into actionable insights, and 91.67% cost savings, improving RAG-based product review analysis and insight generation with measurable gains in productivity improvement, cost reduction, customer experience, and speed to market.
adidas uses Databricks AI Search, Databricks BGE Large, Databricks Model Serving, and Unity Catalog to support RAG-based product review analysis and insight generation. adidas needed a more scalable review-analysis stack because its legacy chatbot was not built for GenAI or RAG, response times were high, and nontechnical users could not easily explore customer sentiment. In practice, the implementation stores or organizes core datasets in Databricks AI Search, governs access and lineage with Unity Catalog, runs transformation or AI logic on Databricks BGE Large, and delivers outputs through Databricks Model Serving. Documents, notes, and knowledge assets are consolidated into Databricks AI Search; Databricks BGE Large applies analytics or model logic; results are surfaced through Databricks Model Serving. The case study reports Driving product innovation through customer feedback 30–40% efficiency gains, Analysts transformed over 2 million customer reviews into actionable insights,...
Documents, notes, and knowledge assets are consolidated into Databricks AI Search; Databricks BGE Large applies analytics or model logic; results are surfaced through Databricks Model Serving.
91.67% cost savings
Adopting more efficient LLMs vastly improved analysis and response time 60% latency reduction
Analysts transformed over 2 million customer reviews into actionable insights
Driving product innovation through customer feedback 30–40% efficiency gains
“The GenAI infrastructure we built is already enabling use cases beyond product reviews,” Rahul said. “Teams are now exploring applications in customer service, knowledge management and other feedback channels.”
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
Databricks Sample Jul 21, 2026 Zapier Zapier needed a better way to support AI-powered self-service analytics, conversational data access, and product personalization because legacy data silos and reliance on a central insights team meant many questions… 2–3 hours delivering ai-powered product and business insights Agent Bricks · Databricks Data + AI Platform · MLflow Databricks Sample Jul 8, 2026 MiQ MiQ needed a better way to support agent-assisted media planning and campaign optimization because massive audience and campaign datasets were spread across separate tools, forcing planners to manually stitch together… Number of campaigns for more than 2,300 advertisers powered by Sigma (since launch) AI Search · Agent Bricks · Databricks Data + AI Platform Databricks Sample Apr 1, 2026 Workday Workday needed a governed, AI-ready data foundation that could serve every line of business — from product telemetry and sales analytics to AI-driven marketing — and let technical and non-technical teams alike build… Every business unit launched sandbox workspaces in 6 months Databricks Data Intelligence Platform · Unity Catalog 