{"type":"post","id":"reducing-token-costs-and-latency-in-amazon-bedrock-eeaa5a","slug":"reducing-token-costs-and-latency-in-amazon-bedrock-eeaa5a","title":"Reducing token costs and latency in Amazon Bedrock AgentCore JSON workloads","description":"AWS describes three changes to a production agent handling large JSON inputs: store bulky artifacts outside conversational state, page large list results on demand, and compact oversized dictionaries.","retrieval_nugget":"AWS describes three changes to a production agent handling large JSON inputs: store bulky artifacts outside conversational state, page large list results on demand, and compact oversized dictionaries.","published_at":"2026-11-18","updated_at":"2026-11-18","record_date":"2026-11-18","date_kind":"published_at","topics":["agent-economics"],"entities":["Amazon Web Services","Amazon Bedrock AgentCore","Flightscape","LangGraph","Amazon S3"],"related_patterns":[],"novelty_label":"new_fact","what_changed":null,"prior_refs":["https://newruntime.com/posts/amazon-bedrock-tokenomics-data-lake-442b50/","https://newruntime.com/posts/architecture-patterns-for-fast-session-startup-on-amazon-f35fee/","https://newruntime.com/posts/optimizing-cost-per-task-and-proving-agent-roi-b45b0e/"],"source_url":"https://aws.amazon.com/blogs/machine-learning/reducing-token-costs-and-latency-in-amazon-bedrock-agentcore-json-workloads","source_urls":["https://aws.amazon.com/blogs/machine-learning/reducing-token-costs-and-latency-in-amazon-bedrock-agentcore-json-workloads"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:reducing-token-costs-and-latency-in-amazon-bedrock-eeaa5a","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/reducing-token-costs-and-latency-in-amazon-bedrock-eeaa5a/","markdown":"https://newruntime.com/posts/reducing-token-costs-and-latency-in-amazon-bedrock-eeaa5a.md","json":"https://newruntime.com/posts/reducing-token-costs-and-latency-in-amazon-bedrock-eeaa5a.json"},"markdown_url":"https://newruntime.com/posts/reducing-token-costs-and-latency-in-amazon-bedrock-eeaa5a.md","next_reads":[{"type":"topic","path":"/topics/agent-economics/","url":"https://newruntime.com/topics/agent-economics/","title":"Agent Economics","reason":"Explore the agent-economics topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/agent-economics.md","json_url":"https://newruntime.com/topics/agent-economics.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}
