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.
The article explains that a context window can be technically complete yet still describe a world that no longer exists. It describes the creation of a deterministic benchmark to measure the cost of acting on stale context. The author built a validity layer to address this issue.
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 .
Enterprise Document Intelligence [Vol. 1 #6quinquies] - Prompt engineering, then context engineering, then loop engineering.
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.
The article argues that Retrieval-Augmented Generation (RAG) is only one tool in NLP, and many real-world problems—such as request classification, free‑text matching, table reading, and OCR noise cleaning—are better served by simpler, cheaper techniques. It emphasizes the importance of selecting the appropriate method for each task and highlights the engineering challenge of knowing which technique to apply.
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.
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 .
Enterprise Document Intelligence [Vol. 1 #7bis] - Tobi Lütke and Andrej Karpathy named the practice in 2025.
Enterprise Document Intelligence [Vol. 1 #7bis] - Tobi Lütke and Andrej Karpathy named the practice in 2025.
Enterprise Document Intelligence [Vol. 1 #7B] - Retrieval is filtering on structured tables: keywords first, TOC second, embeddings last The post Anchor Detection for RAG: Parallel Detectors, Then One LLM Call at the End appeared first on Towards Data Science .
Enterprise Document Intelligence [Vol. 1 #7bis] - Tobi Lütke and Andrej Karpathy named the practice in 2025.
Most AI memory systems keep the newest information—not the most important. Here's how I used the Ebbinghaus forgetting curve to build a better memory engine for LLMs.