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.

The Analytical AI Handbook

Connections

Supports

Bridging Intent and Execution in Agentic Systems The handbook's coverage of design patterns and evaluation methods directly supports bridging intent and execution in agentic systems, providing concrete implementation guidance for that conceptual challenge
Trismik: Evidence-Based Model Switching The handbook's evaluation methodology for LLM-based systems provides the principled foundation for evidence-based model switching decisions that Trismik implements
Understanding is the new bottleneck The handbook directly addresses the 'understanding is the new bottleneck' thesis by providing practitioners with the conceptual vocabulary and evaluation frameworks needed to reason clearly about analytical AI system behavior

Develops into

Understanding Embeddings in Language Models Understanding embeddings is a foundational primitive that the handbook would build upon; the handbook extends from such low-level concepts toward full application design patterns and deployment

Challenges

8 Myths of Software Development with AI The handbook's systematic approach to building analytical AI—with evaluation methods and deployment strategies—implicitly challenges myths about AI software development by grounding claims in structured engineering practice

Related to

6 RAG Architectures Both provide structured architectural guidance for LLM-based systems; the handbook covers primitives and patterns while the RAG architectures piece covers specific retrieval patterns—complementary references for LLM application builders

Supported by

Prompting Claude Fable 5.1 The Analytical AI Handbook and a model-specific prompting guide are complementary practitioner resources—both provide structured frameworks for getting better outputs from AI systems

Type:	link
First published:	Friday, 28 August 2026 at 21:09 UTC
Location:	https://handbook.sutro.sh/
URL:	https://mattwood.fyi/i/af50dc39

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