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.

Cua Documentation — mattwood.fyi

Cua Documentation

Cua is an open-source computer-use automation platform that enables agents to control desktop applications and GUI machines through drivers, sandboxes, and benchmarking tools, with support for real machines, local desktops, and cloud environments.

cua.ai →

Connections

Related to

Introducing Dogwood: runtime verification for AI agents Dogwood provides runtime verification for AI agents while Cua provides sandboxing and benchmarking — both address the reliability and safety infrastructure layer needed for computer-use agents
Munder Difflin: Digital Clone Agent Harness Both are agent harness platforms enabling AI agents to operate in controlled environments — Munder Difflin for digital clones and Cua for desktop/GUI automation with sandboxing
Building an Advanced Agentic Harness Both focus on building agentic harnesses/frameworks for controlling and automating AI agent workflows, with Cua providing the open-source platform infrastructure and 3fa0663b describing advanced harness construction techniques

Supports

Claude Writes macOS Driver for Windows-Only HP Printer Claude writing a macOS driver demonstrates exactly the kind of GUI/desktop automation use case Cua is built to enable — agents controlling real desktop applications through drivers
Bridging Intent and Execution in Agentic Systems Cua's driver and sandbox architecture directly addresses the intent-to-execution gap in agentic systems — providing concrete infrastructure for agents to reliably act on desktop environments
Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks Cua's benchmarking tools for computer-use agents are directly relevant to evaluating and mitigating agent cheating behaviors described in this item about prompt-level mitigation on cyber tasks

Type:	link
First published:	Tuesday, 25 August 2026 at 19:54 UTC
Location:	https://cua.ai/docs
URL:	https://mattwood.fyi/i/24c748a2

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