Skip to content

ArisGlobal optimises prompt caching on Amazon Bedrock to cut inference costs

What happened

AI digest

On 17 November 2026, the AWS Machine Learning Blog reported that ArisGlobal adjusted prompt caching for its life sciences AI engine NavaX on Amazon Bedrock, caching the shared prompt prefix rather than individual source documents. According to the report, this lowers effective input costs and supports more tenants without a proportional increase in cost. So far this is the only first-hand report on the matter, with no follow-up developments or conflicting coverage.

Written by AI from the reports · updated 1 d ago

Timeline

Follow the reports to see the event from each side.

Nov 17
  1. AWS Machine Learning Blog
    How ArisGlobal scaled generative AI inference on Amazon Bedrock

    ArisGlobal runs NavaX, its life-sciences AI engine, on Amazon Bedrock. By caching the shared prompt prefix instead of each per-case document, ArisGlobal cut effective input cost by about 50% and overall monthly inference spend by about 40%, while onboarding more tenants without proportional cost growth.

Heat of this event

Current heat 4·Peak in the comparable range 10(Nov 18 01:00)·Change over 24 hours in the comparable range -50%

02.557.510Nov 1801:00Nov 1810:00Nov 1820:00Nov 1905:00

The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.