AI Systems Under Pressure: Red-Team Before You Ship

Hosted by Krystal Jackson

Fri, Jan 23, 2026

5:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

299 students

Invite your network

Go deeper with a course

Featured in Lenny’s List
Building Agentic AI Applications with a Problem-First Approach
Aishwarya Naresh Reganti and Kiriti Badam
View syllabus

What you'll learn

Define the Real AI Problem

Learn how unclear problem definitions introduce risk in AI systems before prompts or models are involved.

See How AI Systems Break Under Pressure

Examine a real AI workflow to understand how system behavior and problem mismatches create exploitable failures.

Test Assumptions Before You Ship

Learn how a red-teaming mindset helps validate problem framing and surface failures earlier.

Why this topic matters

When AI systems fail, the cause often traces back to early product decisions and untested assumptions about behavior. When key questions go unanswered, systems behave in unexpected ways as prompts, context, and workflows interact. Red-teaming surfaces those failures early by testing system behavior under real-world conditions before shipping.

You'll learn from

Krystal Jackson

AI Standards Development Researcher

Krystal Jackson is an AI security researcher focused on the global security implications of artificial intelligence. She is a Non-Resident Research Fellow with the Center for Long-Term Cybersecurity’s AI Security Initiative, where she studies how advanced AI systems shape risk, resilience, and security outcomes across borders.

Previously, Krystal was a Research Associate at the Frontier Model Forum, where she worked with industry leaders to advance AI-cyber safety and AI security. She also served as an AI Capabilities Analyst at the Cybersecurity and Infrastructure Security Agency (CISA), driving key AI initiatives within the Infrastructure Security Division. Krystal holds an M.S. in Information Security Policy and Management from Carnegie Mellon University.

Career highlights

  • Non-Resident Research Fellow, Center for Long-Term Cybersecurity (AI Security Initiative)
  • Research Associate, Frontier Model Forum, advancing AI-cyber safety with industry leaders
  • AI Capabilities Analyst, CISA, leading AI initiatives in the Infrastructure Security Division
  • Work featured at RSA Conference, Stanford Trust and Safety Research Conference, INFORMS, and AAAI
  • Research roles with the Center for AI and Digital Policy Research Clinic, CSET, and the U.S. Census Bureau
  • M.S., Information Security Policy and Management, Carnegie Mellon University

Sign up to join this lesson

By continuing, you agree to Maven's Terms and Privacy Policy.