How Abnormal AI Screens Billions of Emails with Bedrock AgentCore Sandboxes

AWS ML Blog · rss · 2026-09-15

AWS details how Abnormal AI (protecting 25%+ of the Fortune 500) uses Bedrock AgentCore Code Interpreter for inline email threat detection at billions of messages/day: a three-tier pipeline escalating hardest cases to sandboxed agents, a zero-trust no-egress sandbox design against prompt-injection exfiltration, and a batch analyst agent (100 jobs/week) that drafts heuristics and improves models. 80% of their code changes now involve agents, 40% fully agent-built.

Original post →

More from coding & agent

coding & agent channel →