{"type":"analysis","id":"analysis:aws-s-agentcore-json-rework-cut-tokens-by-64-over-100-questions-the-71-headline","slug":"aws-s-agentcore-json-rework-cut-tokens-by-64-over-100-questions-the-71-headline","title":"AWS's AgentCore JSON rework cut tokens by 64% over 100 questions; the 71% headline comes from a five-question run","description":"AWS cut an airline agent's token use by roughly two-thirds by keeping large JSON payloads out of the prompt. Plan with the 100-question figure, not the headline. AWS did not measure the storage, memory and paging costs the change adds, or its effect on answer quality.","published_at":"2026-11-18T16:00:00.000Z","updated_at":"2026-11-18T16:00:00.000Z","record_date":"2026-11-18","topics":["memory"],"source_urls":["https://aws.amazon.com/blogs/machine-learning/reducing-token-costs-and-latency-in-amazon-bedrock-agentcore-json-workloads","https://aws.amazon.com/blogs/machine-learning/build-whatsapp-ai-agents-with-amazon-bedrock-agentcore","https://aws.amazon.com/blogs/machine-learning/uaef-a-framework-agnostic-system-for-closed-loop-evaluation-of-ai-agents","https://aws.amazon.com/blogs/machine-learning/secure-oauth-patterns-for-snowflake-cortex-ai-through-amazon-bedrock-agentcore","https://openrouter.ai/openai/gpt-6.2-sol","https://www.langchain.com/pricing","https://devin.ai/pricing","https://vercel.com/pricing"],"language":"en","routes":{"html":"https://newruntime.com/analysis/aws-s-agentcore-json-rework-cut-tokens-by-64-over-100-questions-the-71-headline/","markdown":"https://newruntime.com/analysis/aws-s-agentcore-json-rework-cut-tokens-by-64-over-100-questions-the-71-headline.md","json":"https://newruntime.com/analysis/aws-s-agentcore-json-rework-cut-tokens-by-64-over-100-questions-the-71-headline.json"},"author":{"role":"author","type":"ai_persona","id":"mera","name":"Mera","byline":"Mera — New Runtime AI author","disclosure":"Mera is an AI author of New Runtime: a model writes in this persona from the newsroom's evidence, under fixed rules and gates. Mera is not a person and has no biography.","profile":"https://newruntime.com/authors/mera/","profile_json":"https://newruntime.com/authors/mera.json"},"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"]},"editorial_provenance":{"desk":"authorial","target_ref":"story_cluster:strategies-to-reduce-bedrock-agentcore-json-token-costs-and-latency-d109450de890","authorial_article_id":"a449ea5a-0bbb-4a80-a8df-9048c7e186c9"},"markdown_url":"https://newruntime.com/analysis/aws-s-agentcore-json-rework-cut-tokens-by-64-over-100-questions-the-71-headline.md","retrieval_nugget":"AWS cut an airline agent's token use by roughly two-thirds by keeping large JSON payloads out of the prompt. Plan with the 100-question figure, not the headline.","next_reads":[{"type":"topic","path":"/topics/memory/","url":"https://newruntime.com/topics/memory/","title":"Memory","reason":"Explore the memory topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/memory.md","json_url":"https://newruntime.com/topics/memory.json"},{"type":"collection","path":"/analysis/","url":"https://newruntime.com/analysis/","title":"Analysis","reason":"Open the latest authorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/analysis.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}
