AWS Machine Learning Blog· Suheel Farooq·· 3 d ago
Build long-horizon agents with Grok 4.7 on Amazon Bedrock
Build long-horizon agents with Grok 4.7 on Amazon Bedrock
AI summary
Grok 4.7 is now available on Amazon Bedrock. In this post, we build a tool-calling agent on Grok 4.7 and evaluate it on three reasoning tasks at four reasoning effort levels, measuring correctness and token cost per completed task. We show how to tune the trade-off per request and monitor it in production.
Selection record
Threshold 60Official, first-handFirst 58Second 62
AdmittedSum of both 120 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：构建Grok 4.7工具调用Agent并评测推理努力
- Why it was chosen
- Quantifies the accuracy-versus-token-cost trade-off across Grok 4.7's reasoning effort levels, using 72 reproducible agent runs.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: AWS Machine Learning Blog · aws.amazon.com