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.
More from coding & agent
- GitHub Copilot app adds /ask to question agents mid-task without waiting — DanWahlin · 2026-09-15
- Perplexity says GPT-6 Astra can run full workflows with far fewer human check-ins — imjustnewatai · 2026-09-15
- Stop reading terminals: build with AI entirely in realtime HTML pages — nptacek · 2026-09-15
- Coding agents must survive a day without saying 'You're right, sorry' before ASI, researcher jokes — andrey_kurenkov · 2026-09-15
- Claude Code's Function Hooks bring Express-style middleware to plugins — nicolascraske · 2026-09-15
- Review agent commits in parallel with zero context via the show-me skill — lucasmeijer · 2026-09-15