Episode

Sponsored: Teaching AI agents the rules of the road

Podcast
Risky Bulletin
Published
May 24, 2026
Duration seconds
1614
Processing state
not_requested
Canonical source
https://risky.biz/RBNEWSSI129/
Audio
https://dts.podtrac.com/redirect.mp3/media3.risky.biz/RBNEWSSI129.mp3
JSON
/v1/public/podcasts/risky-bulletin-5423259/episodes/sponsored-teaching-ai-agents-the-rules-of-the-road
Markdown
/podcast/risky-bulletin-5423259/sponsored-teaching-ai-agents-the-rules-of-the-road.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/risky-bulletin-5423259/episodes/sponsored-teaching-ai-agents-the-rules-of-the-road/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/risky-bulletin-5423259/sponsored-teaching-ai-agents-the-rules-of-the-road.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

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.