How Omada Health scaled patient care by fine-tuning Llama models on Amazon SageMaker AI

This post is co-written with Sunaina Kavi, AI/ML Product Manager at Omada Health.

Omada Health, a longtime innovator in virtual healthcare delivery, launched a new nutrition experience in 2025, featuring OmadaSpark, an AI agent trained with robust clinical input that delivers real-time motivational interviewing and nutrition education. It was built on AWS. OmadaSpark was designed to help members identify their own motivational challenges like emotional eating, improve food decisions, set goals, and sustain lasting behavior change. The following screenshot shows an example of OmadaSpark’s Nutritional Education feature, demonstrating how members receive personalized nutrition education in real time.

In this post, we examine how Omada partnered with AWS and Meta to develop this healthcare-aligned AI solution using Llama models on Amazon SageMaker AI. We explore the technical implementation, architecture, and evaluation process that helped Omada scale personalized nutrition guidance while maintaining their commitment to evidence-based care.

The opportunity for ...