Tool
Gemma
10 cases from 8 companies use Gemma in their stack. 2 report results in production. Tasks: Evaluate models, Build an assistant over internal docs, Label data with LLMs, Retrieve and rank from millions of items and 4 more. Methods: LLM-as-a-judge, Few-shot prompting, Hybrid search, Synthetic data generation (LLM), RAG and 24 more. Companies: Instacart, Atlassian, VK, Mercari and 4 more.
| Automating Search Relevance Assessment at Scale with LLM-as-a-Judge | e-commerce | 2026-08 | |
| Semantic IDs: Product Understanding at Scale | e-commerce | 2026-06 | |
| Developing a RAG System on the History of Bashkortostan Using a Benchmarking MethodologyUF | UF | general | 2026-05 |
| Advancing semantic search for millions of Rovo users | saas-b2b | 2026-03 | |
| Greeting + Does RAG Even Work? | fintech | 2025-11 | |
Building RAG-Like Systems for Few-Shot Intent Classification in Narrow Domains![]() | ![]() | banking | 2025-05 |
| LLMs. Leaks, exploits and abuse | — | general | 2025-05 |
| LLMs vs. Annotators: How to Get High-Quality Text Labeling | adtech | 2024-11 | |
| In IDE Code Retriever | — | general | 2024-11 |
Fine-Tuning an LLM to Extract Dynamically Specified Attributes![]() | ![]() | marketplace | 2024-09 |

