Method

Context engineering

Curating instructions, metadata and layers of context supplied to LLMs.

20 cases from 15 companies apply Context engineering. 3 were checked in an online A/B test; 8 report results in production.

Typical tasks: Answer questions over data, Make metric definitions consistent, Evaluate models, Build a data platform and 7 more. Companies: Databricks, LinkedIn, Netflix, Grab, Spotify, Khan Academy and 9 more. Often combined with: LLM-as-a-judge, Text-to-SQL, MCP, Human in the loop, Semantic layer and 44 more.

Inside LinkedIn's data context layer: curating trustworthy context for humans and agentssocial2026-10
How AI is transforming analytics at Grabfood-delivery2026-08
GenRec: Towards LLM-Native Recommendation at Netflixmedia-streaming2026-07
Building Query Expert MCP: Using RAG to Build an Analytics Agent That Goes Beyond Text-to-SQLfintech2026-06
Insights at Scale With Agentic AI: How AI Ready Data is Transforming Commercial Life Scienceshealthtech2026-06
Thinking Fast & Slow: How Databricks Built High-Speed and Deep Research Agentsgeneral2026-06
Building Higher Quality Genie Agents (fka Genie spaces): How to Ensure Accuracy and Trustgeneral2026-06
Behind the curtain: Key learnings from building Geniegeneral2026-06
How We Built Agent Mode for Geniegeneral2026-06
Encoding Your Domain Expert: The Context Layer Behind Spotify's Data Assistantmedia-streaming2026-06
How Khan Academy Is Building a Better AI Tutor: Our Most Recent Learningsedtech2026-05
Daedalus and the Data Labyrinthfood-delivery2026-04
Building Biz Ask Anything: From Prototype to Productmarketplace2026-03
LinkedIn Cognitive Memory Agent: long-term memory for personalizing LLM agentssaas-b2b2026-03
The AI Evolution of Graph Search at Netflixmedia-streaming2026-01
A Simulation and Evaluation Flywheel to Develop LLM Chatbotsfood-delivery2026-01
Building a multi-agent pipeline for NL-to-SQL analyticssocial2026-01
Understanding Etsy's Vast Inventory with LLMsmarketplace2025-10
The 95% Breakthrough: Ditching RAG for MAG in Wix's AI-Powered Data Discoverysaas-b2b2025-07
Supercharging Discovery in Search with LLMse-commerce2024-09