# Amazon — Adaptive agentic intelligence framework using Strands Agents

- Company: Amazon (amazon.com)
- Announced: 2026-10-21T21:23:26+00:00
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://aws.amazon.com/blogs/machine-learning/adaptive-agentic-intelligence-framework-using-strands-agents/
- Record: https://forck.live/items/26178-adaptive-agentic-intelligence-framework-using-strands-agents
- Subject: Bedrock / Nova
- Models affected: llama3.2:1b, llama3.2-vision

Amazon's walkthrough shows how to build the Adaptive Agentic Intelligence Framework with Strands Agents, routing routine requests to local small language models and complex ones to Amazon Bedrock. The framework answers a cost problem: sending every request, even a routine status check, to one large cloud model drives up API costs, adds unpredictable latency and rules out offline operation. AAIF splits processing into three layers, with a 1B-parameter llama3.2:1b orchestrator classifying each request and dispatching it without hardcoded rules. Local tools handle device telemetry and camera-feed vision through Ollama, while a get_expert_insights tool calls Amazon Bedrock through boto3 for multi-step analysis. The setup runs on a Raspberry Pi with 8 GB of memory, entirely in the cloud, or in a hybrid mix, because routing logic is separated from the tools. The post cites Belcak et al. at NVIDIA, who argue small language models are sufficiently powerful and more economical for many agentic invocations.

## Evidence

Verbatim from https://aws.amazon.com/blogs/machine-learning/adaptive-agentic-intelligence-framework-using-strands-agents/:

> Instead of routing all requests to a single large model, AAIF uses small language models (SLMs) to handle routine tasks locally. More complex requests are routed to cloud-hosted models through Amazon Bedrock .

---

Record: https://forck.live/items/26178-adaptive-agentic-intelligence-framework-using-strands-agents
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md