?? 500 ML and LLM use cases from 100+ companies! How do top companies design their AI systems? We updated our database of practical ML use cases, including real-world LLM and Gen AI applications ?? https://lnkd.in/dWiPV4MR
关于我们
A collaborative AI observability platform. Evaluate, test and monitor any AI-powered product. Open-source ML monitoring and LLM evaluation.
- 网站
-
https://evidentlyai.com
Evidently AI 的外部链接
- 所属行业
- 软件开发
- 规模
- 2-10 人
- 总部
- San Francisco
- 类型
- 私人持股
- 创立
- 2020
- 领域
- machine learning、data science、mlops、observability和llm
地点
-
主要
US,San Francisco
Evidently AI 员工
-
Svetlana Popova
Technical Lead
-
Elena Samuylova
Co-Founder Evidently AI (YC S21) | Open-source tools to evaluate and monitor AI-powered products.
-
Emeli Dral
Co-founder and CTO Evidently AI | Machine Learning Instructor w/100K+ students
-
Daria Maliugina
Community manager ?? @ Evidently AI. We are building THE open-source tools to test, evaluate and monitor ML models
动态
-
?? How to create LLM test datasets? An in-depth guide on how to build evaluation datasets with synthetic data and how test datasets work for RAG and AI agent simulations ?? https://lnkd.in/dqD4C-9i
-
-
?? How to build LLM evaluation datasets? You can write test cases, use existing data, collect data from test users, use public benchmarks, or generate synthetic data. Watch the video as Elena Samuylova explains how ?? https://lnkd.in/dQ_wEKRG
-
-
???? Webinar and live demo: how to evaluate RAG systems! Join us on March 10 as Elena Samuylova and Emeli Dral explain evaluation techniques and show how to effectively use synthetic data for RAG testing ?? https://lu.ma/fv2i1sdv
-
-
?? LLM evaluation methods and metrics, explained simply! We put together a guide that covers automated LLM evaluation methods, from semantic similarity to LLM judges, and shows when to use them ?? https://lnkd.in/dUD6BTvM
-
-
?? How to evaluate an LLM app? Create a test dataset, manually label responses, and design an LLM evaluation system to run automated evals. A step-by-step walkthrough by Elena Samuylova ?? https://lnkd.in/dbfcF3K8
-
-
?? How do you evaluate an LLM app? We put together an illustrated beginner’s guide to LLM evals: 6000+ words exploring the topic from all angles ?? https://lnkd.in/dsQWQEm9
-
-
?? New RAG evaluation features are now available in Evidently Open-source! Score chunk-level relevance, evaluate generation quality, use LLM judges, and more. Check out our latest release ?? https://lnkd.in/dAKktx6h
-
-
?? 100+ LLM benchmarks and datasets! We put together a database of LLM benchmarks for knowledge, reasoning, conversation, and coding abilities, as well as safety and multimodal LLM benchmarks? ?? https://lnkd.in/dirqEVNB
-
-
? Evidently is changing for the better—and so does our API! Unified Reports and Test Suites, intuitive dashboard panels, and more. Here’s everything you need to know about the new API ?? https://lnkd.in/dNpAgPtE
-