Deepchecks and AWS Partner to Advance LLM Evaluation While Maintaining Data Privacy

A major milestone for AI governance and trustworthiness—Deepchecks and AWS have officially partnered to bring advanced LLM (Large Language Model) evaluation capabilities to Amazon SageMaker, while ensuring data privacy remains uncompromised.

At AWS re:Invent, Dr. Swami Sivasubramanian, VP of AI and Data at AWS, unveiled one of Amazon SageMaker’s most significant releases to date: SageMaker Partner AI Apps. This deep integration embeds Deepchecks’ AI evaluation tools—alongside other leading solutions—directly into Amazon SageMaker AI and Amazon SageMaker Unified Studio, enabling seamless, automated, and privacy-preserving LLM evaluations within AWS’s robust ecosystem.

Why This Partnership Matters

1️⃣ LLM Evaluation at Scale – As AI models grow in complexity, ensuring their reliability and fairness becomes increasingly challenging. Deepchecks’ integration enables real-time, automated model assessments, improving AI transparency and governance.

2️⃣ Privacy-First AI Monitoring – Organizations can now evaluate their models without compromising sensitive data, a crucial feature for industries handling regulated information, such as healthcare and finance.

3️⃣ Seamless AI Workflows – The Deepchecks x AWS integration allows data scientists, ML engineers, and enterprises to conduct end-to-end evaluations within SageMaker’s AI development environment, ensuring streamlined, efficient AI deployments.

This collaboration represents a major leap forward for AI accountability, giving organizations the tools they need to monitor, assess, and trust their AI models—all while keeping data secure.

📖 Read more about this game-changing partnership here: Deepchecks x AWS Partnership