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.

6 RAG Architectures — mattwood.fyi

Connections

Supports

Understanding Embeddings in Language Models Understanding embeddings is foundational to RAG systems; the embeddings explainer provides the conceptual underpinning needed to choose between the six RAG architectures
Bridging Intent and Execution in Agentic Systems RAG architectures are a core mechanism for bridging intent and execution in agentic systems by grounding LLM responses in retrieved context
Designing APIs for Agents - Freestyle RAG architectures inform how APIs should be designed for agents, particularly around context retrieval and knowledge injection patterns

Challenges

How I Over-Engineered My Book Both address over-engineering in technical systems; the RAG architectures piece explicitly helps practitioners avoid over-engineering, directly paralleling the book's lesson about unnecessary complexity

Related to

How I Under-Engineered my Book Both pieces advocate for appropriate simplicity in system design rather than defaulting to complex implementations

Develops into

Building an Advanced Agentic Harness Simple RAG patterns naturally evolve into components of advanced agentic harnesses; the RAG architecture survey informs the retrieval layer of more complex agent builds

Supported by

Tangle: Visual ML Pipeline Editor Tangle's visual pipeline composition tool could be used to build and visualize the RAG architectures described, making complex retrieval pipelines more accessible without code setup

The Analytical AI Handbook Both provide structured architectural guidance for LLM-based systems; the handbook covers primitives and patterns while the RAG architectures piece covers specific retrieval patterns—complementary references for LLM application builders
Agent Memory as a File Format RAG architectures and Memoryfields both address the problem of external memory/retrieval for AI agents; Memoryfields argues for simpler file+vector-index approach vs. the complex multi-layer RAG architectures
Declarative Attention: Models Controlling Their Own Attention RAG architectures also grapple with selective context retrieval and attention over long contexts; Declarative Attention offers a model-native alternative to retrieval-based context management

Type:	link
First published:	Thursday, 27 August 2026 at 15:44 UTC
Location:	https://www.lighthousenewsletter.com/p/rag-is-simpler-than-you-think
URL:	https://mattwood.fyi/i/abf1974e

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