AWS cuts agent token costs 71% and latency 80% on 23MB JSON workloads with three strategies

AWS ML Blog · rss · 2026-11-18

AWS ML Blog details how it built a production agent for airline ops platform Flightscape (40+ tools, 20MB+ JSON inputs) that originally exceeded 15s latency per call. Using three composable strategies, token consumption dropped up to 71% and average latency up to 80% on a representative 23MB payload.

Stack: LangGraph on Amazon Bedrock AgentCore with memory persistence; Bedrock Guardrails filters responses.

The three strategies:

Includes TypedDict definitions for PersistedState/GraphState, code for dehydratestate, and a companion GitHub repo.

Original post →

More from coding & agent

coding & agent channel →