Tech Meridian ← LIVE FEED
PROMY MERIDIAN RU

NEWS · CODING · #3133

Advait Patel presents a playbook for zero-trust AI agent systems at QCon AI

Advait Patel (Senior SRE at Broadcom) presented a practitioner playbook at QCon AI on securing production AI agent systems: moving defenses from prompts to the tool layer, enforcing scoped workload identities, mitigating prompt-injection via tool output controls, and building audit-ready observability and kill switches to protect sensitive data while maintaining fast deployment. The talk draws on real incident lessons and existing cloud/compliance practices (AWS/GCP, SOC 2/ISO).

KEY POINTS

  1. Advait Patel (Senior SRE at Broadcom) presented a practitioner playbook at QCon AI on securing production AI agent systems: moving defenses from prompts to the tool layer, enforcing scoped workload identities, mitigating prompt-injection via tool output controls, and building audit-ready observability and kill switches to protect sensitive data while maintaining fast deployment.
  2. The talk draws on real incident lessons and existing cloud/compliance practices (AWS/GCP, SOC 2/ISO).
  3. AI agents can autonomously access and exfiltrate sensitive data; practical, audit-ready controls are needed to run them safely in production.

WHY IT MATTERS

AI agents can autonomously access and exfiltrate sensitive data; practical, audit-ready controls are needed to run them safely in production.

SOURCES & TIMELINE

1