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.

Bag of Decisions Reranker

Connections

Related to

Semantic ID-based Generative Retrieval for Podcast Discovery at Spotify Both tackle retrieval/ranking quality problems — Spotify's semantic ID generative retrieval and Bag of Decisions reranker represent different stages of the same pipeline, with Bag of Decisions potentially improving post-retrieval ordering
UNREAL: Unifying Retrieval and Long-Context with a Single Model Both address the retrieval quality problem — UNREAL unifies retrieval and long-context in one model, while Bag of Decisions improves reranking post-retrieval via multi-question rubrics; complementary approaches to the same search relevance challenge
Engineering a Calibrated Classifier Model Both concern calibration of probabilistic scores — Bag of Decisions relies on summing calibrated LLM probability scores across questions, making classifier calibration directly relevant to its reliability
Contrastive Language Model (CLM) Contrastive Language Models and Bag of Decisions both explore alternatives to standard single-score relevance signals, using structured comparison or decomposition to produce richer document scoring

Develops into

Evolution of Text Classification: From Bag-of-Words to Modern APIs Bag of Words was the foundational text classification paradigm; Bag of Decisions is an explicit conceptual evolution — replacing term frequency vectors with LLM-scored question rubrics as the scoring primitive

Supports

Automating Eval Design and Hillclimbing with Claude Automating eval design with Claude parallels Bag of Decisions' approach: both use LLM-generated question rubrics to decompose vague quality signals into structured yes/no criteria for scoring

Supported by

How Long Contexts Fail Bag of Decisions Reranker addresses selective information prioritization, which is a mitigation strategy for context confusion and distraction - reranking helps surface relevant decisions rather than overwhelming agents with all context

How To Use Decision Models For Evals 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

Type:	link
First published:	Monday, 12 October 2026 at 17:23 UTC
Location:	https://softwaredoug.com/blog/2026/10/08/bag-of-decisions.html
URL:	https://mattwood.fyi/i/d8d4c52f

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