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.

Serve Markdown to AI Agents with Accept Headers

Connections

Related to

How AgentCore Gateway Supports the MCP 2026-07-28 Spec Both tackle the web/HTTP layer for agentic AI: AgentCore Gateway supports MCP spec at the API gateway level while this item improves content delivery through HTTP content negotiation
The New MCP Roadmap Both concern the evolving infrastructure layer for AI agents — MCP roadmap defines agent communication protocols while Accept header negotiation defines how agents should retrieve web content

Supports

Designing APIs for Agents - Freestyle Both address how to design web APIs and content delivery specifically for AI agent consumption; the Accept header approach is a concrete implementation of agent-friendly API design principles
Understanding Embeddings in Language Models Clean Markdown served to agents improves the quality of text fed into embedding and retrieval pipelines, directly enhancing the embedding quality discussed in understanding language model embeddings
Ways to think about token pricing Serving stripped Markdown instead of full HTML directly reduces token consumption, making this a practical technique for optimizing token usage costs discussed in token pricing analysis
Bridging Intent and Execution in Agentic Systems Content negotiation for AI agents bridges the gap between web intent (human-readable HTML) and agent execution needs (clean structured text), directly addressing intent-to-execution alignment in agentic systems

Slideops: Repository Slide Deck Generator Both treat code artifacts as structured knowledge to be served to agents or humans in richer formats — Slideops as slide decks, Markdown serving via Accept headers — emphasizing format-aware documentation delivery

Supported by

Agent Memory as a File Format Serving Markdown to AI agents via Accept headers is complementary infrastructure to Memoryfields' file-based Markdown memory approach - both treat Markdown as a first-class data format for agent interaction

Type:	link
First published:	Wednesday, 26 August 2026 at 22:32 UTC
Location:	https://acceptmarkdown.com/
URL:	https://mattwood.fyi/i/4faad2c8

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