Agent-led devs need serverless OpenSearch, Amazon claims

https://image.theregister.com/5249081.jpg?imageId=5249081&x=0&y=0&cropw=100&croph=90.85&panox=0&panoy=0&panow=100&panoh=90.85&width=1200&height=683

System relies on a proprietary storage layer as AWS moves to separate storage and compute to fit mega AI demands

Amazon has re-engineered its serverless OpenSearch database service, separating storage and compute in a move it claims will benefit developers faced with new demand characteristics of agentic AI.

The new serverless system would avoid the problem of users paying for idle compute capacity between demand bursts, the vendor claims.

Speaking to The Register, Tia White, Director of OpenSearch, AWS said: “Collections can shrink all the way to zero when nothing's happening. We have mitigated the cold start problem, so they spin back up in seconds when traffic is needed as agents restart. It auto-scales 20 times faster than before.”

AWS promises a fully managed search and vector engine designed for customers building AI agents, offering up to 60 percent cost savings compared to the cost of OpenSearch Service clusters provisioned...

Copyright of this story solely belongs to theregister.com. To see the full text click HERE

Read more

https://image.cnbcfm.com/api/v1/image/108330581-1783302717764-gettyimages-2266485037-NVIDIA_GTC.jpeg?v=1783302852&w=1920&h=1080

SemiAnalysis: Nvidia delays its next-gen AI rack system Kyber NVL144 by 12+ months to 2028 due to PCB manufacturing issues, and cancels its NVL72x2 architecture

Sponsor Posts Fast, affordable law for startups — Soxton automates startup legal so founders can move faster and sleep better. We handle incorporation, advisor, employment and commercial contracts. Join the waitlist for early access! Stop vibe coding analytics — Equals AI turns questions about your business into auditable spreadsheet models and dashboards.