Episode

Context Poisoning is Killing Your AI Agents: How to Stop it

Podcast
Chain of Thought | AI Agents, Infrastructure & Engineering
Published
Mar 25, 2026
Duration seconds
2658
Processing state
not_requested
Canonical source
https://share.transistor.fm/s/e9df3b6f
Audio
https://media.transistor.fm/e9df3b6f/ed763f48.mp3
JSON
/v1/public/podcasts/chain-of-thought-ai-agents/episodes/context-poisoning-is-killing-your-ai-agents-how-to-stop-it
Markdown
/podcast/chain-of-thought-ai-agents/context-poisoning-is-killing-your-ai-agents-how-to-stop-it.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/chain-of-thought-ai-agents/episodes/context-poisoning-is-killing-your-ai-agents-how-to-stop-it/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/chain-of-thought-ai-agents/context-poisoning-is-killing-your-ai-agents-how-to-stop-it.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

Michel Tricot co-founded Airbyte, the open source data integration platform with 600+ free connectors that hit a $1.5 billion valuation. Now he's building the company's next product: an agent engine, currently in public beta. His thesis is that agents don't fail because models are bad. They fail because the data feeding them is wrong: context poisoning is killing them. Michel demos this live. A simple Gong query through raw API calls burned 30,000 extra tokens and took three minutes. Chain of Thought is hosted by Conor Bronsdon.