技巧官方一手
用 Strands Agents 构建自适应智能体框架：本地 SLM 处理简单任务，复杂请求走 Amazon Bedrock
Adaptive agentic intelligence framework using Strands Agents
精选理由
AWS 教程教你怎么用 Strands Agents 搭一套混合架构：简单活儿让 Ollama 本地小模型干，难活儿丢给 Bedrock 云端模型，还带 IoT 监控实例。
AWS 在机器学习博客发布 Adaptive Agentic Intelligence Framework（AAIF）的构建教程，基于 Strands Agents 实现。该框架用 Ollama 运行本地小语言模型（SLM）处理日常任务，把复杂请求经 Amazon Bedrock 路由到云端模型。教程以 IoT 监控为示例场景，完整演示搭建流程。核心思路是按任务复杂度分流，降低本地延迟和云端调用成本。
原文 · AWS Machine Learning Blog
Adaptive agentic intelligence framework using Strands Agents
The Adaptive Agentic Intelligence Framework (AAIF), built with Strands Agents, handles routine tasks locally with small language models and routes complex requests to cloud models through Amazon Bedrock. This post walks through building AAIF with local SLMs through Ollama and Amazon Bedrock, using an Internet of Things monitoring scenario.
