Non-Brand Data | Cornellius Yudha Wijaya | Substack

🚀 Join Non-Brand Data for free AI + Data Science tips

RAG-To-Know🔍

RAG Evaluation Monitoring and Logging with Opik

NBD Lite #53 How you splitting your data can affect the RAG performance

May 14, 2025 • Cornellius Yudha Wijaya

9 Chunking Strategies to Improve RAG Performance

NBD Lite #52 How you splitting your data can affect the RAG performance

Mar 10, 2025 • Cornellius Yudha Wijaya

Explainable RAG for More Trustworthy System

NBD Lite #51 Evaluate both the retrieval and generation in systematic ways

Feb 14, 2025 • Cornellius Yudha Wijaya

Enhance RAG Accuracy with Corrective-RAG (CRAG)

NBD Lite #50 Implement self-reflection for the retrieved documents

Feb 6, 2025 • Cornellius Yudha Wijaya

career

I Have Worked in Data Science for Almost a Decade. These Skills Aged Better Than I Expected

The tools changed much faster than the work underneath them*

Sep 17 • Cornellius Yudha Wijaya

My book is out: Python Data Analysis, Fourth Edition

Co-written with my co-author, and what the year of writing it was like.

Jul 4 • Cornellius Yudha Wijaya

Fix it or throw it away: deciding what to do with an AI output

The harder part is knowing which problems you can fix and which ones mean starting over.

Jun 30 • Cornellius Yudha Wijaya

Why Most GenAI Workflows Need a Review Loop

A Better Prompt Is Not Enough

Jun 24 • Cornellius Yudha Wijaya

python

Building a Minimal Agent Harness in Python

A beginner-friendly guide to running agent code in another process and stopping it when it takes too long.

Jul 16 • Cornellius Yudha Wijaya

My book is out: Python Data Analysis, Fourth Edition

Co-written with my co-author, and what the year of writing it was like.

Jul 4 • Cornellius Yudha Wijaya

Batch Screening Fundamentals with Financial Modeling Prep and Streamlit

Build a Lightweight Stock Screener For Your Fundamental Analysis

Jan 7 • Cornellius Yudha Wijaya

Building an Open-Source Microservice for Financial Data Retrieval with Financial Modelling Prep

Company-Fundamental Tracking Microservice that is Suitable For Your Requirements.

Dec 6, 2025 • Cornellius Yudha Wijaya

🚀 Join Non-Brand Data for free AI + Data Science tips

Recent posts

Module 14: Writing the results and recommendations

A SQL result can be correct and still make a weak report. The table gives the numbers, but the reader still needs to know what they mean and what they…

Oct 4 • Cornellius Yudha Wijaya

Module 13: When a SQL query needs optimization

In this module, we will learn how to read a PostgreSQL query plan and decide whether an index is worth keeping.

Oct 4 • Cornellius Yudha Wijaya

Module 12: Checking whether your result is right

Let's learn how to check a SQL result before we use it in a report or recommendation.

Oct 2 • Cornellius Yudha Wijaya

Module 11: Using window functions without changing the row count

Let’s learn how to calculate totals, running values, and ranks while keeping every order row in the result.

Oct 2 • Cornellius Yudha Wijaya

Module 10: Breaking a query into steps with subqueries and CTEs

Let's learn how to split a long SQL query into named steps and check the result from each step.

Oct 2 • Cornellius Yudha Wijaya

Context Engineering for Data Science

Helping AI solve the right data science problem

Oct 2 • Cornellius Yudha Wijaya

Recommendations

The Data & AI Ecosystem

Dylan Anderson

Daily Dose of Data Science

Avi Chawla

Ruben Dominguez

AI Product Management: A World Beyond AI

JaserBK

Dean of Big Data Newsletter

Dean of Big Data 🎓 #DOBD

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts