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.

Ledge: Runnable Markdown Notes

Ledge is a markdown notebook tool for developers that executes shell commands, code, SQL queries, and AI prompts directly within notes, with persistent shell state and real-time output streaming across macOS, Windows, Linux, and mobile.

ledge.sh →

Connections

Supports

Vibe Coding's Evolution Into Mainstream Development Ledge exemplifies vibe coding's evolution into mainstream development by making executable notebooks accessible to developers who want to blend documentation with live code execution
What Even Is An OS Now? Ledge represents a novel OS-adjacent tool where the notebook becomes a runtime environment, supporting the broader question of what an OS interface looks like when documentation and execution merge

Related to

Building a Software Factory: Merging 1000 PRs in a Week Both address developer productivity tooling; Ledge's persistent shell state and real-time streaming targets the same high-throughput engineering workflows needed to merge large volumes of PRs efficiently
Claude Code Changelog Ledge's integration of AI prompts directly within markdown notes is complementary to Claude Code's agentic coding capabilities, potentially serving as a notebook interface for AI-assisted development workflows
Skillsync - Portable AI Context for Coding Agents Both tools aim to provide persistent, portable context for coding agents and developers; Ledge through stateful shell sessions in notes, Skillsync through portable AI context across coding agents
Code Execution with MCP: Building Efficient AI Agents Both tools enable code execution within developer workflows; Ledge embeds execution in markdown notes while the MCP approach enables code execution for AI agents, both addressing the need for runnable environments

Type:	link
First published:	Thursday, 1 October 2026 at 09:05 UTC
Location:	https://ledge.sh/
URL:	https://mattwood.fyi/i/11ee1904

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