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.

Thinking Orbs: AI thinking indicator for React

Connections

Supports

Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning Thinking Orbs visualizes the AI 'thinking' process for users; Thinking Before Thinking explores meta-reasoning and inference scaling — the component makes visible exactly the cognitive states that paper theorizes about
Thinking Fast and Slow in AI: the Role of Metacognition Thinking Orbs' nine hand-tuned states map to distinct cognitive modes; 'Thinking Fast and Slow in AI' explores metacognition stages that these visual states are designed to communicate to end users
An App Can Be a Home-Cooked Meal 'An App Can Be a Home-Cooked Meal' argues for personal, crafted software; Thinking Orbs being 'hand-tuned' with nine states reflects that same artisanal, intentional approach to even small UI details

Related to

Personal Agent Protocol Personal Agent Protocol defines how agents communicate state and intent; Thinking Orbs provides the visual layer that surfaces those states to humans, together forming a UX stack for agent-facing interfaces
ascii.rest: Animated ASCII Art for Web Pages Both are UI/animation components for web interfaces — Thinking Orbs provides animated AI state indicators while ascii.rest provides animated ASCII art, both targeting visual feedback in applications
Introducing Ember-1 Both are React-ecosystem UI components targeting AI-native product interfaces, suggesting a growing ecosystem of purpose-built front-end primitives for AI applications

ThinkingCap: Gemma-4-26B-A4B Token Efficiency Both deal with AI 'thinking' processes — ThinkingCap optimizes thinking tokens computationally while Thinking Orbs visualizes the thinking indicator for users; complementary perspectives on the same underlying concept
ThinkingCap: Gemma-4-26B-A4B Token Efficiency Both concern the 'thinking' phase of AI reasoning — ThinkingCap optimizes thinking token volume while Thinking Orbs provides UI indicators for the thinking process, reflecting shared interest in making reasoning transparent and efficient

Type:	link
First published:	Thursday, 15 October 2026 at 19:42 UTC
Location:	https://libraries.dev/orbs
URL:	https://mattwood.fyi/i/5c6d6b3c

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