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 AI Operating Layer — mattwood.fyi

Connections

Supports

Cedar Policy Cedar Policy's fine-grained authorization framework is architecturally complementary to and likely used within enterprise AI agent governance platforms like Coder's
Secrets Don't Belong in Config Secrets management best practices ('secrets don't belong in config') are directly relevant to Coder's self-hosted cloud environments where security and compliance are core features
AI Coding and the Bug Selection Problem The bug selection problem in AI coding is a governance/oversight challenge that Coder's centralized management platform aims to mitigate through enterprise controls
Agentic Coding: LLM Agents, Testing, and Hallucination Risks Agentic coding risks like hallucination and testing failures are directly addressed by Coder's centralized governance and compliance layer for managing AI coding agents

Develops into

SWE-bench Science: Coding Agents for Engineering Tasks SWE-bench analyzes coding agents for engineering tasks; Coder's platform represents the enterprise infrastructure layer that operationalizes such agents at scale with governance controls

Related to

Introducing Dogwood: runtime verification for AI agents Dogwood's runtime verification for AI agents and Coder's AI operating layer both address the enterprise need for oversight and safety controls over deployed coding agents

Supported by

Introducing System One Models and Jev TypeSafe AI's System One Models and Jev represent a concrete instantiation of an AI operating layer — infrastructure tooling that sits between raw models and application-level usage
Mireye: Physical World AI Infrastructure Mireye represents a concrete instantiation of an AI operating layer concept, providing the physical-world data infrastructure that sits beneath AI agent operations
Can Rivian Self Driving Edge Past Tesla and Waymo? The AI operating layer framework contextualizes how Rivian's autonomous stack compares architecturally to Tesla's vertically integrated approach and Waymo's software-platform model

Type:	link
First published:	Tuesday, 1 September 2026 at 20:36 UTC
Location:	https://coder.com/ai-operating-layer
URL:	https://mattwood.fyi/i/0c4fc938

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