# Sponsored: Teaching AI agents the rules of the road

Page: https://stenobird.com/podcast/risky-bulletin-5423259/sponsored-teaching-ai-agents-the-rules-of-the-road
Text version: https://stenobird.com/podcast/risky-bulletin-5423259/sponsored-teaching-ai-agents-the-rules-of-the-road.md
Podcast: [Risky Bulletin](https://stenobird.com/podcast/risky-bulletin-5423259)
Published: 2026-05-24T20:24:50+00:00
Episode link: https://risky.biz/RBNEWSSI129/
Audio file: https://dts.podtrac.com/redirect.mp3/media3.risky.biz/RBNEWSSI129.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/risky-bulletin-5423259/episodes/sponsored-teaching-ai-agents-the-rules-of-the-road
Duration seconds: 1614

## Resource

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.

## Actions

- request_transcript: `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.
- read_markdown: `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.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.