Secure AI Agents with Guardrails

​An agent that can read your issues and docs can also leak them, or obey an instruction hidden inside them. Most teams give every agent one shared API key and hope the prompt holds. Live, I give each agent its own identity in Keycloak, check every action against the user's permissions with OpenFGA, and block a prompt injection planted in a GitHub issue. Part 3 of 7 in the Agentic AI Systems series.

​This session is hosted on Maven. Register at https://maven.com/p/0fb6dd to get the Zoom link.

​What you will leave with

• ​Give every agent its own identity: Each agent signs in with its own scoped credentials, never a shared key.

• ​Check each action against the user's permissions: The agent sees and does only what the person it works for may.

• ​Block prompt injection hidden in your data: Catch an instruction planted in an issue before the agent follows it.

​Join this free live lesson to watch an AI agent get its own identity, its permissions and a guardrail against prompt injection, then secure your own system in the Agentic AI Buildcamp for Engineers & PMs.