[un]prompted Security Practitioner Con 2026

[un]prompted

Every session of [un]prompted 2026: Nicholas Carlini, Daniel Miessler, Heather Adkins + 50 more who brought what they've learned from the edge: agents, detection, forensics, governance, llm security, offensive, prompt injection, threat intel. "It feels like a warp point in time: the moment security has to decide whether to stay deterministic, or jump into this non‑deterministic, AI‑driven world. But if we can pull just 2% of the people around us up one level, from "I type into ChatGPT like Google" to "I use agents and tools," then I believe we can change companies and countries.” - Gadi Evron.

  1. May 28

    Ep 1 | Gadi Evron - Day One Remarks | [un]prompted 2026

    Day One opening and closing remarks from Gadi Evron at [un]prompted 2026.Gadi Evron is CFP Chair, [un]prompted and CEO, Knostic.

    3 min

  2. May 28

    Ep 2 | Gadi Evron - Day Two Remarks | [un]prompted 2026

    Day Two opening and closing remarks from Gadi Evron at [un]prompted 2026. Gadi Evron is CFP Chair, [un]prompted and CEO, Knostic.

    14 min

  3. May 28

    Ep 3 | Dan Hubbard - Zero Day Is Now the Space Between a Prompt and Prod | [un]prompted 2026

    Day 1 | Stage 1 Dan Hubbard kicks off [un]prompted with a poem. Dan Hubbard is VP of Research, Vectra AI. Watch on YouTube: https://www.youtube.com/watch?v=cUMJTM9egiM

    3 min

  4. May 28

    Ep 4 | Heather Adkins & Four Flynn - Evaluating Threats & Automating Defense at Google | [un]prompted 2026

    Day 1 | Stage 1 VP of Security Engineering from Google discusses advancing code security with a comprehensive overview of Google's AI security strategy. Shows how to evaluate emerging cyberattack capabilities and demonstrates how tools like CodeMender are helping build intrinsically safer software. Heather Adkins is VP of Security Engineering, Google. Four Flynn is VP Security and Privacy, Google DeepMind. Watch on YouTube: https://www.youtube.com/watch?v=B_7RpP90rUk

    20 min

  5. May 28

    Ep 5 | Joshua Saxe - The Hard Part Isn't Building the Agent: Measuring Effectiveness | [un]prompted 2026

    Day 1 | Stage 1 As AI coding tools drive the cost of building security agents toward zero, the hard problem becomes knowing whether they'll actually work against real attacks and vulnerabilities not seen before. Presents a practical journey from naive precision/recall metrics to multi-dimensional evaluation that captures reasoning quality, evidence gathering, and tool-calling logic. Shows how proper measurement unlocks automated agent improvement using genetic algorithms and AI coding tools. Includes live demo. Joshua Saxe is AI Security Technical Lead, Meta. Watch on YouTube: https://www.youtube.com/watch?v=rO2yA52U_i4

    22 min

  6. May 28

    Ep 6 | Shruti Datta Gupta & Chandrani Mukherjee - Security Guidance as a Service | [un]prompted 2026

    Day 1 | Stage 1 Explores how to provide consistent security guidance at scale, especially in AI-first environments. Discusses building an AI-Native Security Guidance as a Service that centralizes security knowledge and powers multiple defensive AI capabilities with consistent, evaluated and bespoke guidance. Shruti Datta Gupta is Product Security Engineer, Adobe. Chandrani Mukherjee is Product Security Engineer, Adobe. Watch on YouTube: https://www.youtube.com/watch?v=SMEZowlcyyo

    22 min

  7. May 28

    Ep 7 | Jeffrey Zhang & Siddh Shah - Guardrails beyond Vibes | [un]prompted 2026

    Day 1 | Stage 1 Shares how Stripe is using AI agents to streamline high-friction security workflows including threat modeling and security request routing. Covers practical design choices that made these agents reliable in practice: modular orchestrator/child architectures, targeted tools, structured inputs/outputs, and validation to reduce variance and improve determinism. Walks through measuring and improving agent quality over time using offline and online evaluation loops. Jeffrey Zhang is Security Engineer, Stripe. Siddh Shah is Software Engineer, Stripe. Watch on YouTube: https://www.youtube.com/watch?v=KrKk8BGPeQA

    21 min

  8. May 28

    Ep 8 | Paul McMillan & Ryan Lopopolo - Code Is Free: Securing Software | [un]prompted 2026

    Day 1 | Stage 1 An AI-maximalist vision of securing software in the agentic future. Presents engineering-first ways to improve security of projects with zero-friction additions. Advocates for using LLMs to write code and security, arguing that if engineers use LLMs for code, they should use them for security too. Paul McMillan is Security Engineer, OpenAI. Ryan Lopopolo is Member of Technical Staff, OpenAI. Watch on YouTube: https://www.youtube.com/watch?v=U2O14Jd3MBU

    25 min
See All (58)

About

Every session of [un]prompted 2026: Nicholas Carlini, Daniel Miessler, Heather Adkins + 50 more who brought what they've learned from the edge: agents, detection, forensics, governance, llm security, offensive, prompt injection, threat intel. "It feels like a warp point in time: the moment security has to decide whether to stay deterministic, or jump into this non‑deterministic, AI‑driven world. But if we can pull just 2% of the people around us up one level, from "I type into ChatGPT like Google" to "I use agents and tools," then I believe we can change companies and countries.” - Gadi Evron.

Information

You Might Also Like