Towards Data Science - NFHN Reader

A team cut their AI inference bill by more than half. Three months later, customer…
Use coding agents to power your knowledge base

Latest

Using Gemma 4, Ollama, OpenAI Agents SDK, and Tavily MCP to build a lightweight research…
Why memorizing for the exam doesn’t mean you understand the subject
Enterprise Document Intelligence [Vol.1 #M1] – The thesis behind every architectural choice in this series
How to smash through data / ML behavioural interviews
I benchmarked raw chat history, vector-only RAG, and a context graph on the same multi-agent…
A reproducible benchmark on latency, cost, and reproducibility, and where agents actually earn their keep.
Whether you should stick to a classic Ordinary Least Squares regression, introduce interaction terms, or…
Beat the 8GB VRAM limit. Learn how to run three different LLMs on a single…
Enterprise Document Intelligence [Vol.1 #7C] – One LLM call ranks the candidates with reasons. The…

A practical data engineering onboarding workflow for environment setup, automated testing, and AI-assisted development.
A practical walkthrough using text-to-SQL as the example
How Gemini solved my Pandas problem in seconds, and why data science fundamentals still matter…
The PCIe transfer latency is silently bottlenecking your agentic inference. Here is how building a…
Getting reliable, readable responses out of your LLM, and knowing which tool to reach for
How unit economics should set your classification cutoff, and why they rarely do.
Most LLM applications need a clear workflow, not an autonomous agent. Here’s how to build…
Budgets for AI tokens can’t be infinite, no matter how much hyperscalers wish they were
A single model hands you a single answer and no sense of how much it…

Enterprise Document Intelligence [Vol.1 #7B] – Retrieval is filtering on structured tables: keywords first, TOC…
Enterprise Document Intelligence [Vol.1 #7A] – Stop searching strings. Filter line_df and toc_df. Pick anchors…
Why one-hot encoding isn’t always the best approach, and alternative encodings
The intuition behind neural networks and why they need activation functions.
Understanding how LLMs interact with the world around them, from returning data to taking action
For decades, the existence of the hydrophobic core, a region in the 3D structure of…