What is mattwood.fyi?

A live, structured feed of riffs and links from Matt Wood, Chief AI & Technology Officer at AWS — readable by people and queryable by agents as a typed knowledge graph.

Is there an API and is it free?

Yes. A public, read-only query API is available with no authentication and no API keys. See https://mattwood.fyi/openapi.json and https://mattwood.fyi/docs.

How should an AI agent use this site?

Fetch https://mattwood.fyi/feed.json for the full structured feed, or query the API for keyword/semantic search and the connection graph. See https://mattwood.fyi/agents/ for when-to-use guidance.

How Keras 3 Modernized Expedia's Lodging Ranking Stack

Connections

Supports

How One Tech Company Created 13 New Types of Jobs Because of A.I. Expedia's ML infrastructure modernization exemplifies how tech companies upgrade internal capabilities with AI, supporting the narrative of AI creating new specialized engineering roles and workflows
How Frontier Teams Are Reinventing AI-Native Development Expedia's Keras 3 adoption is a concrete example of frontier teams reinventing AI-native development practices in production recommendation systems

Related to

Fireworks AI: Specialized Intelligence Infrastructure Fireworks AI's specialized intelligence infrastructure parallels Expedia's effort to build specialized ML infrastructure for domain-specific ranking tasks
Baseten: High-Performance AI Inference Platform Baseten's high-performance inference platform addresses similar enterprise ML infrastructure challenges that Expedia faced when upgrading their ranking stack with Keras 3
Training Azerbaijani Language Models on Amazon SageMaker AI Both describe industry ML practitioners leveraging specific ML frameworks/platforms (Keras 3 vs SageMaker) to modernize production training pipelines for domain-specific models
Together AI: Research-Driven Inference and Training Platform Both involve industrial-scale ML inference infrastructure optimization for production systems, with Together AI and Expedia both focusing on high-performance model serving pipelines

Supported by

Tangle: Visual ML Pipeline Editor Tangle's visual ML pipeline editor directly supports the kind of multi-framework model training and deployment workflows described in Keras 3's modernization of Expedia's ranking stack
Dynamic Programming: Unifying Principle Across Algorithms Lodging ranking with Keras involves neural network training, which the new item explicitly covers as a DP application—backpropagation is a specific instance of dynamic programming on computation graphs

Type:	link
First published:	Tuesday, 11 August 2026 at 19:56 UTC
Location:	https://medium.com/expedia-group-tech/how-keras-3-helped-modernise-expedia-groups-lodging-ranking-stack-7fec96f052fd
URL:	https://mattwood.fyi/i/d63c59c9

I'm Matt Wood, and this is For Your Information. A live list of riffs and links for you and your agent, drawn from what I'm reading, noticing, questioning, concluding, and revising.

Connections