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.

Building a skill optimization loop

Connections

Develops into

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation The simple 'run-diff-improve' skill optimization loop is formalized into COLLEAGUE.SKILL's automated expert-knowledge distillation pipeline.
SIA: Self Improving AI Framework The single-skill improvement loop generalizes into SIA's multi-agent coordinated self-improvement framework.
LLMs reward expertise 'Building a skill optimization loop' represents the systematic institutionalization of the individual expertise advantage described — moving from Tao-level personal expertise to engineered skill loops
Why some people mow a lawn better than others The empirical findings on human CPP strategies could directly inform automated skill optimization loops for robotic or autonomous path-planning agents

Mario meets Pareto Both explicitly address optimization loops for skill/stat builds — the Mario Kart piece applies Pareto efficiency to character/kart stat tradeoffs, while 'Building a skill optimization loop' addresses systematic optimization of competing performance dimensions
Micro-Agent: Beat Frontier Models with Collaboration inside Model API Both target improving task performance through internal iteration—collaboration inside an API call versus a skill-refinement loop.

Supported by

Why some people mow a lawn better than others The lawn-mowing study is fundamentally about skill optimization loops — participants implicitly develop better coverage strategies through iteration, directly illustrating how humans build and refine optimization skills

Type:	link
First published:	Friday, 26 June 2026 at 12:00 UTC
Location:	https://www.warp.dev/blog/building-a-skill-optimization-loop
URL:	https://mattwood.fyi/i/0fad234d

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