Hands-On Workshop: Evaluating LLM Apps with Deepchecks and SageMaker AI

The upcoming Deepchecks event is "Hands-On Workshop: Evaluating LLM Apps with Deepchecks and SageMaker AI". 🚀

In this session, Philip Tannor (CEO & Co-Founder, Deepchecks) and Noam Bressler (VP R&D, Deepchecks) will lead a hands-on workshop about evaluating LLM apps with Deepchecks and SageMaker AI. 🔥

📆 Date & Time: January 30th, 2025 | 08:00 AM PST

➡️ Register here: https://www.linkedin.com/events/hands-onworkshop-evaluatingllma7284571402433683458/

We will cover the methodologies and best practices for evaluating LLM systems — from initial proof-of-concept experiments to production-grade evaluation & monitoring.

Topics that will be covered:

✅ Initial Experiments: We’ll cover how to design experiments that provide meaningful insights into retrieval accuracy, version comparison, generative quality, and overall effectiveness.

✅ LLM Evaluation: Setting up continuous evaluation pipelines for LLM systems in production environments.

✅ Metrics & Optimization: Key metrics for evaluating LLM systems—such as relevance scoring, response accuracy, hallucinations, toxicity, etc.

✅ Integration with AWS: Learn how to seamlessly integrate Deepchecks into AWS SageMaker AI for scalable, production-grade LLM Evaluation & Monitoring.