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. The same query through Airbyte's context store ran in one minute and used a fraction of the context window. Conor and Michel dig into why RAG alone won't cut it, what a "context engineer" actually does, how Airbyte tracks entities across Salesforce, Zendesk, and Gong without embeddings, and whether the SaaS apocalypse playing out in public markets is overblown.
Chapters:
0:00 Intro
0:20 Meet Michel Tricot, CEO of Airbyte
2:27 Data Got Us to the Information Age. Context Gets Us to Intelligence.
4:48 How Context Poisoning Breaks Agents
7:49 Why Airbyte Customers Stopped Loading Into Warehouses
10:12 Live Demo: Context Store vs Raw API Calls
10:38 What Does a Context Engineer Actually Do?
14:14 RAG Isn't Dead, But How We Build It Will Die
16:41 30K Wasted Tokens Without Proper Context
22:22 Cross-System Joins: Zendesk, Gong, and Salesforce
26:12 The Open Source Agent Connector SDK
29:45 The SaaS Apocalypse Is Overblown
36:09 From Data Pipes to Agent Infrastructure
38:51 What Agents Need to Get Right by Summer
40:48 Memory Is Just Another Form of Context
43:07 Outro
About the Guest:
Michel Tricot is the CEO and co-founder of Airbyte, the open source data integration platform used by thousands of companies to move data between systems. Before Airbyte, he led data ingestion and distribution engineering at LiveRamp. Airbyte raised at a $1.5 billion valuation and offers 600+ free connectors. The company recently launched the public beta of its agent engine, which includes a context store, agent connector SDK, and MCP integration.
Guest Links:
Show Links:
Thanks to our presenting sponsor Galileo. Download their free 165-page guide to mastering multi-agent systems at galileo.ai.
