Deep-dive on securing AI agents at BSidesSF

On April 27, Blue41’s co-founders Tim Van hamme and Thomas Vissers gave a deep dive on productionizing agentic apps reliably and securely at this year’s dragon-themed BSides San Francisco.

Taming dragons is risky—so is deploying agentic apps. Like dragons, they’re unpredictable, with threats like hallucinations, non-determinism, vast input spaces, and attacker prompt injections. We show how open-source tools tame the beast, so you can confidently deploy AI agents in production.

BSidesSF is a non‑profit security conference held annually for two days alongside RSA Conference. It serves as an open, community‑driven forum where everyone is a participant, not just an attendee, sparking conversations on the “next big thing” rather than yesterday’s headlines. By pairing peer‑reviewed technical talks with informal collaboration, BSidesSF helps expand and deepen the collective body of information‑security knowledge while keeping it freely accessible—thanks to the combined efforts of its passionate organizers, participants, and generous no‑strings‑attached sponsors.

Tim and Thomas at BSides San Francisco