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.

Harness Engineering — mattwood.fyi

Connections

Develops into

DeepSeek Harness: Plugin Architecture DeepSeek Harness's plugin architecture is a concrete instantiation of harness design patterns; this guide provides the principled theoretical framework that generalizes such implementations
AI Literacy Superpowers AI Literacy Superpowers explicitly builds on Harness Engineering as a core concept, serving as a marketplace and documentation hub that extends this framework into governance and oversight tooling

Supports

Ornith-1.5: Self-Scaffolding to Self-Improvement Ornith-1.5's self-scaffolding to self-improvement directly requires the progressive hardening and architectural constraints described in harness engineering to prevent runaway self-modification
Bridging Intent and Execution in Agentic Systems Bridging intent and execution in agentic systems is precisely what harness engineering's architectural constraints and context engineering address - providing the structural layer that closes the intent-execution gap

Related to

Building an Advanced Agentic Harness Both directly address building agentic harness architectures; 'Building an Advanced Agentic Harness' covers overlapping structural concerns that this comprehensive guide formalizes and extends with GC and hardening techniques
Munder Difflin: Digital Clone Agent Harness Munder Difflin's digital clone agent harness is a practical harness implementation; this guide's context engineering and GC principles would directly inform its architecture
EnvHarness: Awakening Static Worlds for Agent Learning EnvHarness for awakening static worlds shares the core harness engineering challenge of managing environment state and progressive agent learning that this guide addresses through GC and hardening techniques

Type:	link
First published:	Thursday, 27 August 2026 at 16:18 UTC
Location:	https://habitat-thinking.github.io/ai-literacy-superpowers/plugins/ai-literacy-superpowers/explanation/harness-engineering/
URL:	https://mattwood.fyi/i/3544a4c6

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