AWS redesigns cloud infrastructure for AI agents, decoupling compute from storage to enable instant scaling and zero idle costs

AWS launched next-generation OpenSearch Serverless on Thursday, a fully managed search and vector database designed specifically for agentic workloads that can instantly scale up when agents trigger tasks and scale back down to zero when idle.

The key technical change decouples compute from storage, allowing compute to scale up in seconds and down to zero so customers pay $0 when agents are idle—a shift from the prior Serverless version where at least one instance had to remain operational because storage and compute were coupled.

At launch, OpenSearch Serverless will integrate natively with AI development platforms like Vercel and Kiro, enabling developers to deploy production-ready search and vector backends for agents without managing infrastructure.

Cloudflare reported that bots accounted for 31% of overall HTTP traffic over the last six months, with AI crawlers, search engines, and assistants making up roughly a quarter of all bot requests during that period; Li Yi Ohlsen, senior product manager at Cloudflare, stated that non-human traffic will exceed human traffic sometime in the first half of 2027.