Method

LLM classification / extraction

Using an LLM for classification, tagging and attribute extraction.

34 cases from 24 companies apply LLM classification / extraction. 6 were checked in an online A/B test; 11 report results in production.

Typical tasks: Evaluate models, Match entities, Build an assistant over internal docs, Catch fraud and abuse and 11 more. Companies: DoorDash, Ramp, Databricks, Gusto, Yandex, Avito and 18 more. Often combined with: RAG, Human in the loop, LLM-as-a-judge, LLM labeling, Few-shot prompting and 68 more.

Developing a model to detect harmful content from OpenChat titles and descriptionssocial2026-08
Building Jarvis Pro: Route first, answer laterfood-delivery2026-08
How We Turn Learner Search into Content Intelligenceedtech2026-07
Agentic Risk Operationsfintech2026-06
Building an AI Database for Agentic GTM Operationssaas-b2b2026-06
From Dashboards to Decisioning: How We Rebuilt Marketingsaas-b2b2026-06
BI for AI: Transforming OTel Agent Telemetry into Enterprise Analyticsgeneral2026-06
From Prompt to Classifier: A Production Case Studysaas-b2b2026-06
AgentOps in Production: Infrastructure for LLM Agents and Support Automation for Yandex Personal Servicesmedia-streaming2026-05
Developing a RAG System on the History of Bashkortostan Using a Benchmarking Methodologygeneral2026-05
How LLMs Take Clustering to a New Levelretail2026-05
Automating Receipt Collection: Apple Intelligence for On-Device Inferencefintech2026-04
Universal Document Processing at Gusto: From One-Off Parsers to a Self-Service Platformsaas-b2b2026-02
Mind the Gap: Using LLMs to bridge behavioral silos in multi-vertical recommendationsfood-delivery2025-12
Atlassian Rovo Dev Research: What Types of Code Review Comments Do Developers Most Frequently Resolve?general2025-11
Understanding Etsy's Vast Inventory with LLMsmarketplace2025-10
A scalable LLM approach to enhancing chatbot knowledge with user-generated contentfood-delivery2025-08
Scaling Catalog Attribute Extraction with Multi-modal LLMse-commerce2025-08
How LLM Automates Work at Avitoclassifieds2025-05
Internships on the LLM Team: Several LLM Deployments at Avitoclassifieds2025-05
High-Speed Multimodal Moderation: LLMs and VLMs in Real Productionmarketplace2025-05
Labeling Product Cards with LLMse-commerce2025-05
Cycle Paths, Shashlik and Sakura: How Yandex Maps Built Seasonal Leisure Recommendationsgeneral2025-05
AI Sales Agents: Architecture, Bottlenecks and the Evolution of Capabilitiessaas-b2b2025-05
From RAG to Richness: How Ramp Revamped Industry Classificationfintech2025-01
How DoorDash leverages LLMs for better search retrievalfood-delivery2024-11
Unleashing the power of large language models at DoorDash for a seamless shopping adventurefood-delivery2024-10
Fine-Tuning an LLM to Extract Dynamically Specified Attributesmarketplace2024-09
Extracting Product Attributes from PDFs using PAE Frameworkretail2024-06
Advanced application of GigaChat at Rabota.ru. Recommendations and auto-moderationclassifieds2024-05
Building DoorDash's product knowledge graph with large language modelsfood-delivery2024-04
Extracting Job Roles in Job Ads: A Journey with Generative AIclassifieds2024-01
How Whatnot Utilizes Generative AI to Enhance Trust and Safetymarketplace2023-09
Your Opinion Matterse-commerce2022-07