Skip to content

AWS shares three strategies to cut token use and latency in AgentCore JSON workloads

What happened

AI digest

On 18 November 2026, the AWS Machine Learning Blog published an article on three composable strategies for reducing token costs and latency in Amazon Bedrock AgentCore JSON workloads. The article uses a training-scheduling optimisation agent on Flightscape's flight operations platform as its scenario; the agent must handle JSON payloads of more than 20 MB. In benchmarks with a representative 23 MB payload, the team says the strategies cut token consumption by up to 71% and average latency by up to 80%. The article currently gives only these benchmark results and does not disclose the specific content or implementation details of the three strategies.

Written by AI from the reports · updated 19 h ago

Timeline

Follow the reports to see the event from each side.

Nov 18
  1. AWS Machine Learning Blog
    Reducing token costs and latency in Amazon Bedrock AgentCore JSON workloads

    As production agents on Amazon Bedrock AgentCore process multi-megabyte JSON payloads, token costs and latency climb. This post shares three composable strategies: offloading heavy artifacts to Amazon S3, on-demand result paging, and dictionary compaction. Together they cut per-turn token use by up to 71% and latency by up to 80%.

Heat of this event

Current heat 5·Peak in the comparable range 9(Nov 18 11:00)·Change over 24 hours in the comparable range –

02.557.510Nov 1811:00Nov 1817:00Nov 1823:00Nov 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.