Towards Data Science June 13, 2026 By Emmimal P Alexander

Larger Context Windows Don’t Fix RAG — So I Built a System That Does

Read the original on Towards Data Science →

Increasing context size in RAG systems doesn’t improve accuracy for aggregation tasks—it makes errors harder to detect. In this article, I benchmark retrieval-based pipelines against a deterministic full-scan engine across 100,000 rows and show why computation queries must be routed away from RAG entirely.

Summary generated by The Flow from the publisher's feed. The full article lives at Towards Data Science.

Towards Data Science

Jul 16

Context Engineering for RAG Question Parsing: From a Raw Question to Typed Fields That Steer Retrieval and Generation

Enterprise Document Intelligence [Vol. 1 #6quater] - Question parsing takes one messy string and writes four typed pieces, each read by a different downstream call The post Context Engineering for RAG Question Parsing: From a Raw Question to Typed Fields That Steer Retrieval and Generation appeared first on Towards Data Science .

By Kezhan Shi

rag

Towards Data Science

Jul 19

Loop Engineering for RAG Question Parsing: The Small Loop That Runs Before Retrieval

Enterprise Document Intelligence [Vol. 1 #6quinquies] - Prompt engineering, then context engineering, then loop engineering.

By Kezhan Shi

llms rag

Towards Data Science

Jun 25

Vector RAG Isn’t Enough — I Built a Context Graph Layer for Multi-Agent Memory

I benchmarked raw chat history, vector-only RAG, and a context graph on the same multi-agent conversations. The results exposed a surprising weakness in relational retrieval.

By Emmimal P Alexander

rag agents

Towards Data Science

May 29

RAG Is Burning Money — I Built a Cost Control Layer to Fix It

Most RAG systems are optimized for answer quality, not cost—and that blind spot gets expensive fast. In this article, I break down a production-ready cost control layer combining semantic caching, query routing, token budgeting, and circuit breaking, achieving an 85% reduction in LLM costs without sacrificing answer quality.

By Emmimal P Alexander

llms rag

Towards Data Science

Jun 24

Finding the right anchors for RAG: keyword, embedding, and TOC signals in parallel

Enterprise Document Intelligence [Vol. 1 #7B] - Retrieval is filtering on structured tables: keywords first, TOC second, embeddings last The post Finding the right anchors for RAG: keyword, embedding, and TOC signals in parallel appeared first on Towards Data Science .

By angela shi

rag

Towards Data Science

Jun 30

Context Engineering for RAG: The Four Typed Inputs Behind Every RAG Answer

Enterprise Document Intelligence [Vol. 1 #7bis] - Tobi Lütke and Andrej Karpathy named the practice in 2025.

By Kezhan Shi

llms rag

Related stories

Context Engineering for RAG Question Parsing: From a Raw Question to Typed Fields That Steer Retrieval and Generation

Loop Engineering for RAG Question Parsing: The Small Loop That Runs Before Retrieval

Vector RAG Isn’t Enough — I Built a Context Graph Layer for Multi-Agent Memory

RAG Is Burning Money — I Built a Cost Control Layer to Fix It

Finding the right anchors for RAG: keyword, embedding, and TOC signals in parallel

Context Engineering for RAG: The Four Typed Inputs Behind Every RAG Answer