Risky Bulletin Podcast
May 25, 2026
Presented by
James Wilson
Technology Editor
In this sponsored interview James Wilson chats with Sondera CEO Josh Devon about why guardrails and instruction files aren’t enough to keep AI agents from going haywire. EDR, DLP and other traditional controls can’t and won’t prevent agents from going rogue.
Josh explains Sondera’s “principle of least autonomy” for agents: let them do useful work, but put them in a deterministic policy harness so they can’t leak secrets, abuse tools or wander off-task.
Sponsored: Teaching AI agents the rules of the road
0:00 / 26:54
Subscribe
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。