Tool
DeepSeek
12 cases from 10 companies use DeepSeek in their stack. 1 was checked in an online A/B test; 4 report results in production. Tasks: Evaluate models, Build an assistant over internal docs, Label data with LLMs, Rank search results and 3 more. Methods: LLM-as-a-judge, Few-shot prompting, LLM labeling, MCP, BM25 and 38 more. Companies: Sber, HSE University, Yandex, Avito, VK and 5 more.
| How We Are Deploying AI at a University | edtech | 2026-05 | |
| The Search of the Future | general | 2026-05 | |
Method of Automated Construction of Production Digital Twins Using LLM Agents![]() | ![]() | manufacturing | 2026-05 |
| EMPI Agent: A Framework for Neurodivergent Students | edtech | 2026-05 | |
| Developing an Aspect-Based Sentiment Analysis System for Online Course Reviews Using LLMs | edtech | 2026-05 | |
Automating the Labeling of News Queries with RAG![]() | ![]() | search-engine | 2025-11 |
| How LLM Automates Work at Avito | classifieds | 2025-05 | |
Attributor, or How an AI Agent Identifies the Advertiser of Digital Campaigns![]() | ![]() | adtech | 2025-05 |
Catch Me If You Can: LLM Quality Control for Customer Service![]() | ![]() | general | 2025-05 |
| POLLUX: Evaluating the Generative Capabilities of LLMs for Russian | general | 2025-05 | |
| Benchmark-driven Time-Series-Augmented Generation | fintech | 2025-05 | |
| LLMs vs. Annotators: How to Get High-Quality Text Labeling | adtech | 2024-11 |



