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.

How To Use Decision Models For Evals

Connections

Related to

Strands Decider: Why Not an Encoder? Strands Decider architectural discussion (why not an encoder) contextualizes the model design choices that this eval guide addresses when selecting appropriate decision models
JevAgentHarness: Decision Models for LLM Agent Control JevAgentHarness uses decision models for LLM agent control, sharing the same core concept of applying classification decision models to agent/eval contexts
Bag of Decisions Reranker Bag of Decisions Reranker similarly uses decision-model-style scoring to rank outputs, sharing the threshold calibration and score interpretation challenges covered in this guide
JevAgentHarness: Decision Models for LLM Agent Control JevAgentHarness uses decision models for LLM agent control, sharing the same core concept of applying decision models to AI evaluation and control scenarios

Develops into

Introducing Strands Decider 2B: Open Source Decision Model Strands Decider 2B is an open-source decision model; this tutorial explains how to operationalize such models by tuning thresholds and interpreting scores for evaluation tasks
Evolution of Text Classification: From Bag-of-Words to Modern APIs Evolution of text classification contextualizes the historical development of classification models; this guide represents the modern applied endpoint of that evolution for evaluation workflows
Introducing Strands Decider 2B: Open Source Decision Model Strands Decider 2B is an open-source decision model, and this guide directly explains how to use such decision models for evals including threshold tuning and score interpretation

Supports

Clef: Open-Source Decision Models and RL Fine-Tuning Clef provides open-source decision models and RL fine-tuning infrastructure; this guide on choosing and tuning decision models for evals is directly applicable to using Clef's models
Clef: Open-Source Decision Models and RL Fine-Tuning Clef's open-source decision models are the category of tools this guide teaches users to deploy and tune, directly supporting practical adoption of Clef-style models in evals
Clef: Open-Source Decision Models and RL Fine-Tuning Both items concern decision models and RL fine-tuning; this eval guide provides practical threshold-tuning and scoring methodology for models like those in Clef
Automating Eval Design and Hillclimbing with Claude Automating eval design and hillclimbing requires exactly the kind of threshold tuning and model scoring interpretation this guide explains, making it directly applicable methodology
Automating Eval Design and Hillclimbing with Claude Automating eval design and hillclimbing with Claude directly benefits from understanding how to choose and tune decision model thresholds as explained in this guide

Type:	link
First published:	Tuesday, 20 October 2026 at 17:44 UTC
Location:	https://x.com/HamelHusain/status/2112588257104216294
URL:	https://mattwood.fyi/i/96329cc9

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