Method

RAG

Retrieval-augmented generation: grounding LLM answers in retrieved documents.

70 cases from 45 companies apply RAG. 8 were checked in an online A/B test; 22 report results in production.

Typical tasks: Build an assistant over internal docs, Evaluate models, Answer questions over data, Rank search results and 12 more. Companies: DoorDash, Yandex, Avito, Sber, Walmart, X5 Tech and 39 more. Often combined with: LLM-as-a-judge, BM25, Supervised fine-tuning, Few-shot prompting, Hybrid search and 128 more.

Building Query Expert MCP: Using RAG to Build an Analytics Agent That Goes Beyond Text-to-SQLfintech2026-06
Beyond Simple Q&A: Building an Agent Orchestrator for Enterprise Analyticsgeneral2026-06
Empowering Non-Technical Users in Pharma With Dashboards and Chatbots Working Together in Databrickshealthtech2026-06
AI Agents for the Frontline: 7-Eleven's GenAI Maintenance Assistantretail2026-06
Scale Trust, Not Headcount: AI-Powered Semantic Engineering at Southern Glazer's Wine & Spiritsretail2026-06
Avi-Pro: An Assistant for Sellers on Avitoclassifieds2026-05
Fast MVPs: Prototyping AI Agent Use Casesretail2026-05
AgentOps in Production: Infrastructure for LLM Agents and Support Automation for Yandex Personal Servicesmedia-streaming2026-05
AI Assistant for Salesclassifieds2026-05
From an LLM Portal to a Factory of Internal Agentsclassifieds2026-05
Lemana-GPT: Building a Secure Corporate Gateway to LLMs and Scaling AI Products in Retailretail2026-05
An AI Tutor and Methods for Evaluating Itedtech2026-05
Developing a RAG System on the History of Bashkortostan Using a Benchmarking Methodologygeneral2026-05
The Search of the Futuregeneral2026-05
From Zero to Agents: Growing a Multi-Agent LLM Platform Inside a Companygeneral2026-05
RAG for Complex Situational Questionsbanking2026-05
An AI Agent as Teacher and Examineredtech2026-05
Building a Coffee Recommender System with LLM and RAGretail2026-05
Scaling Marketing Campaign Forecasting with Generative AIretail2026-05
Building Biz Ask Anything: From Prototype to Productmarketplace2026-03
Our Early Journey to Transform Instacart’s Discovery Recommendations with LLMse-commerce2026-02
The AI Evolution of Graph Search at Netflixmedia-streaming2026-01
Why We Built “BlaBlaCar Data Copilot”: Shifting Data Analysis Leftmobility2025-12
Building The Intent Engine: How Instacart is Revamping Query Understanding with LLMse-commerce2025-11
Automating the Labeling of News Queries with RAGsearch-engine2025-11
How RecSys & LLMs Will Converge: Architecture of Hybrid RecoAgentsadtech2025-10
Using LLMs to infer grocery preferences from DoorDash restaurant ordersfood-delivery2025-09
Decoding Multimodal RAG: Advanced Techniques for Seamless Document Interaction (Part 1)retail2025-08
A scalable LLM approach to enhancing chatbot knowledge with user-generated contentfood-delivery2025-08
Unraveling Rovo search relevancesaas-b2b2025-08
Advancing Menu Content with AI: How DoorDash uses AI to generate menu descriptionsfood-delivery2025-06
How Ramp Fixes Merchant Matches with AIfintech2025-06
Introducing a RAG-based bot to streamline CSsocial2025-06
Building the next generation of job search at LinkedInmarketplace2025-05
Product Applications of Yandex VLMsearch-engine2025-05
Graphs and Agents in Action: Building a CoPilot for All Sber Branchesbanking2025-05
How we use LLMs with RAG in LemanaTECH's ecosystem of IT support ML modelsretail2025-05
Building RAG-Like Systems for Few-Shot Intent Classification in Narrow Domainsbanking2025-05
Product Applications of LLMs: Building an AI Copilot for Editors and Speeding Up Time to Marketbanking2025-05
Make Retrieval Smarter: How We Built Smart Search over a Document Basegeneral2025-05
Retrieval-Augmented Fill-in-the-Middle: An Architecture for Generating Structured Documents with LLMsgeneral2025-05
Function Calling 101: One Agent Instead of a Zoo of Bots—general2025-05
AI in Education: HSE University Case Studiesedtech2025-05
AI Sales Agents: Architecture, Bottlenecks and the Evolution of Capabilitiessaas-b2b2025-05
5 Stops on the Way to LLM in Your Productiongeneral2025-05
Solving Data Discovery at Scale: How Wix Uses RAG and Multi-Agent Systems to Find the Right Data Fastsaas-b2b2025-05
How we built enterprise search to be secure and privatesaas-b2b2025-03
Search Query Understanding with LLMs: From Ideation to Productionmarketplace2025-02
From RAG to Richness: How Ramp Revamped Industry Classificationfintech2025-01
How DoorDash leverages LLMs for better search retrievalfood-delivery2024-11