Episode

Thomson 1: The New $40M Legal AI Model | Thomson Reuters Joel Hron

Podcast: Chain of Thought | AI Agents, Infrastructure & Engineering
Published: Aug 24, 2026
Duration seconds: 3236
Processing state: not_requested
Canonical source: https://share.transistor.fm/s/5ef72d7c
Audio: https://media.transistor.fm/5ef72d7c/b7f578b0.mp3
JSON: /v1/public/podcasts/chain-of-thought-ai-agents/episodes/thomson-1-the-new-40m-legal-ai-model-thomson-reuters-joel-hron
Markdown: /podcast/chain-of-thought-ai-agents/thomson-1-the-new-40m-legal-ai-model-thomson-reuters-joel-hron.md

Actions

POST https://stenobird.com/v1/public/podcasts/chain-of-thought-ai-agents/episodes/thomson-1-the-new-40m-legal-ai-model-thomson-reuters-joel-hron/transcription-requests
Idempotently request low-priority transcript generation for this episode.
GET https://stenobird.com/podcast/chain-of-thought-ai-agents/thomson-1-the-new-40m-legal-ai-model-thomson-reuters-joel-hron.md
Read the agent-friendly Markdown representation of this episode resource.

Summary

Joel Hron, CTO of Thomson Reuters, breaks down how the 175-year-old company trained its own legal AI model, Thomson, for around $40 million by stacking proprietary content and expert judgment on open-source foundations. He explains why owning the model layer beats renting frontier intelligence, and how a rebuilt CoCounsel jumped from 25% to over 70% accuracy.