Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

The prototype is the new PRD. In 2013, Facebook’s development of React changed the way software engineers build and write code. Today, LLMs are transforming that process again. This episode features Tom Occhino, React co-creator and current CPO at Vercel, whose work sits at the center of both shifts. In conversation with 1Password CTO Nancy Wang and Google’s Dev Tagare, Tom explores the platform changes driven by AI-written code, builds a full-stack app in real time, and sets up a deeper discussion on the security risks of agents building software.

Resources for Setup.

Secure secrets for agentic workflows with 1Password MCP Server and Codex As AI agents write, execute, and ship production code, they need access to systems like databases, APIs, and deployment pipelines. With 1Password Environments MCP Server for Codex, instead of putting credentials directly into prompts or files, we provision a secure runtime environment where secrets are mounted, used, and discarded, with user authentication required at the moment of access.

Zero Knowledge Architecture Explained: How 1Password Keeps You Safe Ever wonder what actually happens when you save a password? In this video, we break down the security architecture behind 1Password and explain why even we can't see what's in your vault.

Agents need boundaries | Fotis Chantzis from OpenAI Agents don't fit old identity models. As OpenAI’s Agent Security Lead, Fotis Chantzis has a front-row seat to see how agents push identity systems beyond what they were built to control. That’s where things start to fall apart and where most teams lose control.