# Amazon — Optimizing agent system prompts with Amazon Bedrock AgentCore

- Company: Amazon (amazon.com)
- Announced: 2026-09-16T15:47:39+00:00
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://aws.amazon.com/blogs/machine-learning/optimizing-agent-system-prompts-with-amazon-bedrock-agentcore/
- Record: https://forck.live/items/11422-optimizing-agent-system-prompts-with-amazon-bedrock-agentcore
- Subject: Bedrock / Nova

Amazon's post provides a technical deep dive into the system prompt optimizer within Amazon Bedrock AgentCore, explaining how its recommendation engine works and describing the Single Agent Reflector and the experimental Sub-Agent Reflector designs.

## Evidence

Verbatim from https://aws.amazon.com/blogs/machine-learning/optimizing-agent-system-prompts-with-amazon-bedrock-agentcore/:

> This post is a technical companion to the launch post. We take a deeper look at the system prompt optimizer and explain how its recommendation engine works. We also share evaluation results for the Single Agent Reflector and the experimental, open source Sub-Agent Reflector on two publicly available benchmarks, alongside GEPA and MIPROv2 .

---

Record: https://forck.live/items/11422-optimizing-agent-system-prompts-with-amazon-bedrock-agentcore
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md