Episode

11 Cameras, Dozens of Mics: The AI That Reads the Room

Podcast
Chain of Thought | AI Agents, Infrastructure & Engineering
Published
Aug 27, 2026
Duration seconds
3291
Processing state
not_requested
Canonical source
https://share.transistor.fm/s/dd7626d2
Audio
https://media.transistor.fm/dd7626d2/781743f5.mp3
JSON
/v1/public/podcasts/chain-of-thought-ai-agents/episodes/11-cameras-dozens-of-mics-the-ai-that-reads-the-room
Markdown
/podcast/chain-of-thought-ai-agents/11-cameras-dozens-of-mics-the-ai-that-reads-the-room.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/chain-of-thought-ai-agents/episodes/11-cameras-dozens-of-mics-the-ai-that-reads-the-room/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/chain-of-thought-ai-agents/11-cameras-dozens-of-mics-the-ai-that-reads-the-room.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

Tormod Ree is the chief product and engineering officer at Neat, the Zoom-backed video hardware company putting 11 or more cameras and dozens of microphones into a single meeting room. He explains how Neat's edge models read a room in real time, why the orchestration harness matters more than the models, and how the company trains computer vision without ever touching customer meeting data.