Blog ยท Tag
#strands
2 posts tagged #strands.
Field Notes: Turning prompt caching on for a production Bedrock workload
Strands' BedrockModel ships with prompt caching off. Two kwargs turn it on, one per-model gotcha catches you, and a 10-turn driver measures 99.9% / 99.8% hit ratios on Nova Pro and Sonnet 4.6 against an 8,156-token production system prefix. The per-call usage block proves it in seconds, not waiting on CloudWatch.
Part 3: Building the AI Agent with Strands Agents SDK, Prompt Caching, and AgentCore Memory
How to build the Python agent that runs inside AgentCore: Strands SDK setup, prompt caching that cuts costs by 90%, dual-model strategy, tool definitions, and AgentCore Memory integration.