What each one solves, and runnable code you can paste into a notebook.
What I learned after thinking more carefully about Structured Outputs on messy, incomplete data
Latest
Enterprise Document Intelligence [Vol.1 #B2] - The FAQ inverts every brick of the standard RAG pipeline. Parsing is trivial, retrieval doubles as a cache, and few-shot prompting becomes a retrieval problem too
A framework for building RAG pipelines that introduces complexity in response to observed failure modes, from lexical and hybrid search to reranking and agentic information seeking
The five MLOps monitoring assumptions agents break, and which inherited signals now pass failed runs as healthy.
Quick and simple tips to help you write better agent instructions
How to apply the latest context engineering guidelines to your day-to-day data science work
Enterprise Document Intelligence [Vol.1 #B1] - Three sources of one problem. User typos, fast-typing transcription noise, OCR character errors. Classical spell-check handles one of them. Embeddings carry the rest
Four skills worth adding to your workflow today if you don't want to be left behind
Learn where which coding agent is best
Enterprise Document Intelligence [Vol.1 #B00] - Retrieval answers one kind of question. Classifying a request, matching free text to a reference list, reading a table, cleaning OCR noise: each has a cheaper method that works, and the engineering is knowing which one to reach for
Editor's Picks
A framework for building RAG pipelines that introduces complexity in response to observed failure modes, from lexical and hybrid search to reranking and agentic information seeking
Quick and simple tips to help you write better agent instructions
How to apply the latest context engineering guidelines to your day-to-day data science work
As AI handles more of the execution, what work should belong to agents vs humans and why does that distinction matter?
A practical guide to getting better code, not just more code
Why most agents are just flowcharts in disguise, and what to build instead.
The Variable Newsletter
Sorting through the good, bad, and ambiguous aspects of vibe coding
Don't miss our most-read and -shared stories of the past month
Deep Dives
What each one solves, and runnable code you can paste into a notebook.
Enterprise Document Intelligence [Vol.1 #B1] - Three sources of one problem. User typos, fast-typing transcription noise, OCR character errors. Classical spell-check handles one of them. Embeddings carry the rest
How we stopped reviewing every agent action and started routing human attention where it actually mattered
Bagging hits a wall no amount of trees can break — here's the equation that explains why, and the experiment that proves it
A practical guide to navigate hierarchies, find routes, detect cycles and calculate degrees of separation
A hand-written CUDA inference runtime for Vision-Language-Action robots that decides what to remember, what to forget, and when it's simply too late to think.