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.

Object-Oriented Harness: Evolving Agent Harnesses through OO Design

Connections

Develops into

Your Game Is A Harness Both treat harnesses as first-class design artifacts; OO Harness extends the philosophical framing of 'your game is a harness' into a systematic evolutionary methodology
Testing Behavioral Harnesses for AI Coding Agents Testing behavioral harnesses for AI coding agents provides the evaluation methodology that OO Harness optimization would need to validate its 15% improvement claims

Related to

JevAgentHarness: Decision Models for LLM Agent Control Both focus on LLM agent harnesses - JevAgentHarness uses decision models for control while OO Harness uses object-oriented class hierarchies for optimization, representing complementary architectural approaches to the same problem
JevAgentHarness: Decision Models for LLM Agent Control Both focus on agent harnesses for LLM control; JevAgentHarness uses decision models while OO Harness uses object-oriented class hierarchies as the organizing principle
Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning Both address meta-level optimization of agent behavior—OO Harness evolves harness structure while meta-reasoning scales inference; both push optimization above the base prompt level
Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning Both address meta-level optimization of agent behavior - OO Harness evolves the harness structure itself while meta-reasoning scales agentic inference through pre-computation, both operating above the base agent level

Supports

The Ultimate Guide to Multi-Harness RL OO Harness framework directly exemplifies multi-harness RL concepts by evolving specialized class hierarchies, providing a concrete implementation strategy for the multi-harness RL paradigm
Testing Behavioral Harnesses for AI Coding Agents OO Harness provides a concrete evolutionary framework that directly addresses the behavioral harness testing problem for AI coding agents
Coding Agent Continual Learning: Analysis of ARC-AGI-3 Problem Solving Coding agent continual learning analysis of problem-solving patterns could inform which specialized OO class hierarchies are most beneficial to evolve in the harness optimization process
Coding Agent Continual Learning: Analysis of ARC-AGI-3 Problem Solving Continual learning analysis of coding agents benefits from evolved harness structures; OO Harness's class hierarchy approach could provide the structural scaffolding for iterative problem-solving improvements
The Ultimate Guide to Multi-Harness RL The OO harness design with specialized class hierarchies is a concrete instantiation of multi-harness RL concepts, contributing a structural approach to harness optimization

Challenges

Your Game Is A Harness OO Harness treats agent harnesses as optimizable software artifacts evolved through design principles, while 'Your Game Is A Harness' frames harnesses as structural constraints - the former actively subverts the static harness conception

Supported by

Infinity: A Runtime for Extreme Agent Concurrency Object-Oriented Harness frameworks for evolving agent architectures would be enabled by a runtime like Infinity that can handle the concurrent execution demands of many simultaneous agent harness instances

Type:	link
First published:	Wednesday, 21 October 2026 at 19:33 UTC
Location:	https://arxiv.org/abs/2610.28380
URL:	https://mattwood.fyi/i/0038e9f3

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