# Data Federation, Not Centralization, Is What Enterprise AI Needs

Page: https://stenobird.com/podcast/chain-of-thought-ai-agents/data-federation-not-centralization-is-what-enterprise-ai-needs
Text version: https://stenobird.com/podcast/chain-of-thought-ai-agents/data-federation-not-centralization-is-what-enterprise-ai-needs.md
Podcast: [Chain of Thought | AI Agents, Infrastructure & Engineering](https://stenobird.com/podcast/chain-of-thought-ai-agents)
Published: 2026-07-16T11:30:00+00:00
Episode link: https://share.transistor.fm/s/fcebeaa6
Audio file: https://media.transistor.fm/fcebeaa6/a9655b8c.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/chain-of-thought-ai-agents/episodes/data-federation-not-centralization-is-what-enterprise-ai-needs
Duration seconds: 3162

## Resource

Jitender Aswani was customer zero for Presto at Meta, scaled it at Netflix, and now runs engineering and security at Starburst, the $3.35 billion data platform built on Trino. He explains why the average enterprise has 52 to 200 data sources, why centralizing them will never work, and what happened to Starburst's query volume the day they shipped an MCP server.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/chain-of-thought-ai-agents/episodes/data-federation-not-centralization-is-what-enterprise-ai-needs/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/chain-of-thought-ai-agents/data-federation-not-centralization-is-what-enterprise-ai-needs.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.