# [Live Event] CoreBreak, explained: the AI agent flaw that hit AWS…

Canonical: https://brew.new/templates/redpanda/live-event-corebreak-explained-the-ai-agent-flaw-that-hit-aws

Brand: redpanda.com
Category: general

![Preview of [Live Event] CoreBreak, explained: the AI agent flaw that hit AWS…](https://cdn.brew.new/email-preview-b36a70ef26cc8838-tracking_r57ztc64x910nkd4xj6c77re5n8g84mx-1791998506739.png)

## Email content

CoreBreak: What a Real AI Agent Flaw Proves About Where Guardrails Belong

Hi there,

At Black Hat 2026, researchers found one structural flaw running through three of the biggest AI agent platforms out there. They called it CoreBreak. All three vendors had built their safety measures around the model itself, and CoreBreak proved that if you can skip the model, you skip every one of those protections, too.

Join Redpanda CTO Tyler Akidau and Head of AI Marc Millstone as they break down how the attack actually worked, and what it means that Redpanda had already built the fix before any of this went public.

CoreBreak: What a Real AI Agent Flaw Proves About Where Guardrails Belong

Tue, 10/20 at 9:30AM PT

Register Now

See you there,

Team Redpanda

twitter-1

slack-1

github-1

linkedin-1

Youtube

Youtube

© 2026 Redpanda Data, Inc.

220 Montgomery St. #400, San Francisco, CA 94104

Manage Preferences

[Open and remix this design](https://brew.new/templates/redpanda/live-event-corebreak-explained-the-ai-agent-flaw-that-hit-aws)

[Browse email designs](https://brew.new/browse/templates)