customer_support · healthcare · workflow
Omada Health scales personalized nutrition care by fine-tuning Llama 3.1 on Amazon SageMaker AI
Health coaches at Omada excelled at personalized care, but growing member demand for quick nutritional information created an opportunity to supplement coach capacity with technology that could handle routine analytical tasks and provide immediate nutrition education at scale.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Training data uploaded to S3
Q&A pairs for nutritional education datasets are uploaded to Amazon S3 for model training.
Tools used
Llama 3.1 8BQLoRALangSmithHugging Face estimators
Outcome
OmadaSpark drove significantly higher member engagement — members who used the nutrition assistant were three times more likely to return to the Omada app — and reduced nutrition question response time from days to seconds, with the entire workflow launched in 4.5 months.
Results
Time savedfrom days to seconds
Volumethree times more likely to return to the Omada app
Running since2025
Grounding & classification
Source type: technical build writeup
29 fields verified against source quotes, 3 dropped as unverifiable.
ai agentcontent generationconversational aipersonalizationchat transcriptknowledge basehuman review describedmetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedhealthcarecustomer satisfactionresponse time reductiontime savedtechnical build writeupcustomer supportagentic task executionai draft human approval