ArisGlobal expands Amazon Bedrock generative AI inference
The story so far
ArisGlobal has developed the NavaX AI engine for automating adverse event case processing in the life sciences sector on Amazon Bedrock. With the increasing compliance requirements of enterprise customers, the sharing of prompt prefixes grew by about 150% in 6 months, leading to a more than 200% increase in reasoning cost per case. By adjusting the cache order to prioritize caching shared prefixes, ArisGlobal reduced effective input costs and supported more tenants without proportional cost growth.
AI-written from the reports · Updated 48 minutes ago
Coverage timeline
Follow the coverage to see every side of the story.
- AWS Machine Learning BlogHow ArisGlobal scaled generative AI inference on Amazon Bedrock
ArisGlobal has developed the NavaX AI engine for automating adverse event case processing in the life sciences sector on Amazon Bedrock. With the increasing compliance requirements of enterprise customers, the sharing of prompt prefixes grew by about 150% in 6 months, leading to a more than 200% increase in reasoning cost per case. By adjusting the cache order to prioritize caching shared prefixes, ArisGlobal reduced effective input costs and supported more tenants without proportional cost growth.
Heat over time
Not enough data yet to draw a trend.