Day-Zero: Agents in the Wild

A live adversarial experiment on autonomous agents, compromise, and deceptive success signals.

Autonomous agents are moving into real workflows: using tools, sharing context, making decisions, and acting across systems.

But the success signal can lie.

In Field Report 001: The Penthouse Heist, Day Zero observed multiple AI-assisted attack architectures independently converging on economically meaningful weaknesses within hours.

In Field Report 002: The Infrastructure Strikes Back, the experiment shifted to live defense and showed that raw finding volume was a poor measure of security performance - and that telemetry can miss the failures defenders most need to see.

On June 22, Day Zero returns with Agents in the Wild.

This third experiment places agents in a shared, realistic, multi-tenant environment and attacks the surfaces real deployments expose. Judges and mentors will help evaluate three questions:

• Can agents be induced to do compromising things?

• Can they continue delivering value while compromised?

• Does forewarning create real defense, or just the appearance of defense?

The output will become Field Report 003 in the Day Zero adversarial AI experiment series.

Not a panel. Not a product demo. A field test.

• When: June 22, 2026

• Where: 1900 Broadway, Oakland, CA

• Rules of Engagement: day-zero.dev/rules-of-engagement

• Questions: mail@day-zero.dev

Judges + Mentors

• Apoorv Mehta: Engineering Manager, Product Security

• Arjun Chakraborty: Security AI Research, Microsoft

• Arun Pandiyan Perumal: Site Reliability Engineer, Adobe

• Chetan Jannu: Software Engineer, WhatsApp

• Hannah Kwon: SWE, CX Benchmarking - Model Evals

• Jay Yao: Dev Rel, Memori Labs, Organizer - Gemini Meetup

• Neil Kittleson: CEO, VectorForge

• Prabir Vora: Technical Chief of Staff, Retell AI

• Sujitha Vummaneni: Senior Security Engineer, Ripple

• Thanat Jatuphattharachat: Co-Founder, HolyShred

• Thiyagarajan Palaniyappan: Senior Applied Scientist, AWS

• Tosh Rayadhurgam: Head of Advanced AI, Stripe

• Tripp Roybal: CEO, Kage - Founder, TenguSec

• Tyler D'Silva: Founding AI Engineer, Retell AI

• Usha Ratnam: Staff Software Engineer, DevOps, Ripple

• Venkat Gattupalli: AI Infrastructure & Networking

• More judges announced soon!

All judges and mentors are supporting the event in their personal capacity. Their thoughts and contributions are their own.