Method

Semantic layer

Governed metric and entity definitions (metric views) for BI and LLMs.

40 cases from 31 companies apply Semantic layer. 9 report results in production.

Typical tasks: Make metric definitions consistent, Answer questions over data, Build a data platform, Evaluate models and 5 more. Companies: Databricks, DoorDash, LY Corporation, Ramp, Netflix, Pinterest and 25 more. Often combined with: LLM-as-a-judge, Text-to-SQL, Golden set / benchmark, Human in the loop, Multi-agent system and 39 more.

Agentic Credit Analysisfintech2026-10
DataJunction as Netflix’s answer to the missing piece of the modern data stackmedia-streaming2026-10
Metrics Board: Building an Agent-ready Metrics Layersocial2026-10
Inside Vera, DoorDash’s Data Agentfood-delivery2026-09
Insights at Scale With Agentic AI: How AI Ready Data is Transforming Commercial Life Scienceshealthtech2026-06
Accelerating the Speed to Value of Analytics with Databricks AI/BI & Agentsfintech2026-06
Beyond Simple Q&A: Building an Agent Orchestrator for Enterprise Analyticsgeneral2026-06
Building an Explainable AI Research Agent With Databricks Genieretail2026-06
Building Higher Quality Genie Agents (fka Genie spaces): How to Ensure Accuracy and Trustgeneral2026-06
Databricks on Databricks: Build Your Own Experimentation Platformsaas-b2b2026-06
Metric Views—What They Are, How They Work, and How to Model Themgeneral2026-06
Why Data-Intelligent Agents Win: A Side-by-Side Benchmarkfintech2026-06
Anthropic + Adidas + Databricks: Unlocking 400 Hours of Productivity Weekly with Conversational AIretail2026-06
Supercharging Genie Performance With Metric Viewssaas-b2b2026-06
Building Workforce Intelligence With Unity Catalog and Databricks Geniegeneral2026-06
Empowering Non-Technical Users in Pharma With Dashboards and Chatbots Working Together in Databrickshealthtech2026-06
From Dashboards to Decisioning: How We Rebuilt Marketingsaas-b2b2026-06
Semantic Modeling Best Practices for BI and AIgeneral2026-06
Stop Arguing About Numbers: How Zalando Scales Governance With Unity Catalog and Metric Viewse-commerce2026-06
What Worked, What Didn’t: Virgin Atlantic’s Flight to Trusted Generative BItravel2026-06
Beyond Tables: How Musinsa Built a Self-Optimizing Semantic Layer on Databrickse-commerce2026-06
BI Locked Semantic Models are Dead! Open Semantics Just Entered the Chatretail2026-06
From Power BI DAX to Metric View KPIs: How Mercedes-Benz Korea Built “Talk to Your Data” at Scalegeneral2026-06
Prada Group Serves High-Quality Business Metrics with Lakebaseretail2026-06
A–Z of Unity Catalog Business Semantics: Open and Unified Semantics for Agents, Apps and BIgeneral2026-06
How To Be an Agentic Analystgeneral2026-06
Scale Trust, Not Headcount: AI-Powered Semantic Engineering at Southern Glazer's Wine & Spiritsretail2026-06
Sponsored by: Omni | AI analytics at Condé Nast: What it took to get to productionadtech2026-06
Sponsored by: S&P Global | Leveraging Genie to Remove Friction From Exploratory Data Analysis (EDA)fintech2026-06
Metric Semantic Layer: How Lyft Governs and Scales Key Data Definitionsmobility2026-06
Daedalus and the Data Labyrinthfood-delivery2026-04
Using a semantic package to accelerate analyticssearch-engine2026-03
Building a multi-agent pipeline for NL-to-SQL analyticssocial2026-01
Engineering The Semantic Layer: Principles for Data at Scalemarketplace2025-12
Creating a domain-specific NL-to-SQL MCP serversocial2025-11
Solving Data Discovery at Scale: How Wix Uses RAG and Multi-Agent Systems to Find the Right Data Fastsaas-b2b2025-05
How we build experiments in-housesaas-b2b2024-06
End-to-End Data Infrastructure and Processes for DE/DA/DSfintech2024-05
Using Metrics Layer to Standardize and Scale Experimentation at DoorDashfood-delivery2023-04
Computing Aggregates in VWOsaas-b2b2023-03