You've seen AI coding agents deleting databases and wiping codebases. Current solutions like Claude Code's whitelists/blacklists fail because LLMs are versatile, they can do the same destructive thing in 100 different ways.
This demo demonstrates novel deterministic security guardrails that make agents safe to use in production environments. We'll cover secure secret handling, mTLS for MCP, and introduce Warden, a new deterministic security enforcer that creates boundaries agents cannot cross, regardless of the tools they use.
Real examples from Stakpak's open-source DevOps agent. Your first look at techniques that makes coding agents production-safe, and a reference implementation in Rust.
The founder of Stakpak, a startup building an open-source AI agent that makes DevOps suck less. Previously a founding engineer at Thndr YC S20, and a deep tech crypto startup Liquidity Network. Has a couple of academic publications in distributed systems. Crazy into security, GenAI, and developer experience.
