---
format: "aidr-story-markdown/v1"
id: "8ae9ac7b35af0e95c76f905e31d198c5836f51684aed1f11dac709e548c18818"
canonical_url: "https://aidr.today/8ae9ac7b?lang=en"
title: "Abnormal AI: Amazon Bedrock AgentCore for agentic email security at scale"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-14T21:22:45.000Z"
category: "Agents"
topics: ["amazon","agent","multi-agent","bedrock-agentcore","infra","harness"]
source_urls: ["https://aws.amazon.com/blogs/machine-learning/abnormal-ai-amazon-bedrock-agentcore-for-agentic-email-security-at-scale/","https://aws.amazon.com/blogs/machine-learning/a-shared-agentic-platform-for-wood-mackenzie-on-amazon-bedrock-agentcore/"]
summary: "Learn how Abnormal AI deployed Amazon Bedrock AgentCore Code Interpreter as an ephemeral compute scratch pad for the agents behind its real-time email threat detection at billion-message scale, plus the sandbox design decisions and practical lessons for builders deploying Code Interpreter in production."
---

# Abnormal AI: Amazon Bedrock AgentCore for agentic email security at scale

> [Open the canonical story](<https://aidr.today/8ae9ac7b?lang=en>)

**Published:** 2026-09-14T21:22:45.000Z
**Category:** Agents
**Topics:** amazon, agent, multi\-agent, bedrock\-agentcore, infra, harness

## Summary

Learn how Abnormal AI deployed Amazon Bedrock AgentCore Code Interpreter as an ephemeral compute scratch pad for the agents behind its real\-time email threat detection at billion\-message scale, plus the sandbox design decisions and practical lessons for builders deploying Code Interpreter in production\.

## Sources

- [Story source](<https://aws.amazon.com/blogs/machine-learning/abnormal-ai-amazon-bedrock-agentcore-for-agentic-email-security-at-scale/>)
- [Story source](<https://aws.amazon.com/blogs/machine-learning/a-shared-agentic-platform-for-wood-mackenzie-on-amazon-bedrock-agentcore/>)