Clip / Other

Four security principles for agentic workflows

From Realtime multiplayer, automation, and you! — Idan Gazit, GitHub · ≈11:48

“Defense in depth, one layer is never enough.”

“Never trust agents with secrets.”

“If an agent can know a secret, that secret, you need to treat it as if it's already been compromised.”

“We actually believe that this is going to be a bigger category than interactive AI because automations that run in the background while you sleep, that's the ballgame.”

What’s in it

Four security rules for letting AI agents act autonomously in your systems
Real example: Home Assistant's agent auto-triages GitHub issues by code ownership
Argues background AI automation will outgrow chat-based interactive AI

Watch this moment

Clip transcript

Uh So, uh that's Agentic Workflows. Um the security guardrails, we have sort of four principles that we believe uh everybody should burn into their brains. Uh defense in depth, one layer is never enough. Uh that was always true. Never trust agents with secrets. If an agent can know a secret, that secret, you need to treat it as if it's already been compromised. Uh because you have no idea whether or not somebody's injected the agent to reveal that secret somewhere else. So, if an agent can see the secret, um it's bad. In Agentic Workflows, the secrets are all kept outside of the agent's jail, and when the agent wants to use the secret to call something, it needs to ask the warden, "Hey, mother may I please go talk to that service?" Uh stage and vet all rights, just so that it's auditable, and log everything, just so that it's auditable. Uh and when we give this to existing projects like the Home Assistant project, which is a huge open-source project, um the first uh Agentic Workflow they built was something that looks at every submitted issue, walks the Python stack trace to figure out if the bug is in first-party code or third-party code, closes the issue if it's not their issue, right? That's something that was not possible before AI, not possible with heuristics, uh but is possible now. Agentic Workflows is in public preview today. You can go and kick the tires. So, go ahead, go wild. Uh we actually believe that this is going to be a bigger category than interactive AI because automations that run in the background while you sleep, that's the ballgame.