AIToday
Large Language ModelsAI Business & IndustryAmazon AI BlogPublished: Nov 18, 2026, 01:00 JST

ArisGlobal caches shared prompt first on Amazon Bedrock, cutting inference spend about 40%

Send on LINE
ArisGlobal caches shared prompt first on Amazon Bedrock, cutting inference spend about 40%

3 Key Points

  1. What happened

    ArisGlobal reversed the order of its NavaX requests on Amazon Bedrock so the shared prompt prefix is cached first. It now serves 65% of input tokens from cache, cutting effective input cost by about 50% and monthly inference spend by about 40% at more than 19 billion tokens per month.

  2. Why it matters

    Caching the repeating shared prefix rather than the larger per-case document lets ArisGlobal reuse the same cache entry across requests, cases, and tenants. That supports onboarding more enterprise tenants without proportional cost growth, the company reports.

WHO IT HITSEnterprise IT and AI platform teams running multi-tenant generative AI workloads on Amazon Bedrock may see similar savings by reordering requests to cache stable, repeated prompt prefixes first. The approach requires putting shared instructions and schemas ahead of per-case documents.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

Context & Analysis

ArisGlobal's NavaX engine handles adverse-event reports for pharmaceutical companies, extracting around 130 fields from multipage PDFs across multiple sequential model requests. Each request carries system instructions, customer-specific rules, an extraction schema, and the source document. Two inputs repeat at different scopes: the shared prompt prefix repeats across requests, cases, and tenants using the same agent, while the source document repeats only for requests tied to one case.

The initial design cached the source document because it was the largest part of a request, leaving the growing shared prompt prefix outside the cache. As ArisGlobal added enterprise tenants with distinct compliance requirements, the shared prefix grew substantially over 6 months, and per-case inference costs rose more than proportionally. Because the prefix was reprocessed on every request, its growth compounded with transaction volume.

Rather than adding another checkpoint, ArisGlobal changed the order: the shared prompt prefix comes first, the checkpoint follows, and the document comes last. This trades limited document reuse within one case for prompt reuse across the fleet. The company reports that 65% of input tokens on a typical request are now served from the shared prompt cache, with cache reads consistently exceeding writes in production monitoring.

FAQ
What is NavaX?
NavaX is ArisGlobal's AI engine built for life sciences on Amazon Bedrock. It automates adverse-event case processing by extracting around 130 fields from reports.
How does the new caching setup work?
ArisGlobal places one explicit cache checkpoint immediately after the shared prompt prefix, which is sent first. The per-case document follows the checkpoint and is processed on each request.
Did ArisGlobal change its EU data routing?
No, EU geographic cross-Region inference remains unchanged. Prompt caching operates within the existing inference configuration.
Amazon AI BlogRead Original Article
Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleSuperDial's Agent-to-Agent RCM cuts bot-to-bot calls