PinnedAdam Chang·Jan 24Stop Manual Data Processing! Build a Fully Automated ETL Pipeline with AWSThe Daily Grind of Data Engineers
Adam Chang·Nov 9When Your AI Agent Fails a Test, Check the Judge First: Evaluating a Refund Agent With 7 DeepEval…Several of the test failures in my refund agent's evaluation suite weren't the agent's fault. The LLM judge couldn't see what the customer…A response icon3A response icon3
Adam Chang·Nov 1One thread_id, Four Stores: Refactoring a Tutorial ChatGPT Clone Into a Layered AI AgentThe most valuable change I made to my self-hosted ChatGPT clone was moving one string, thread_id, out of a global variable and into the…A response icon1A response icon1
Adam Chang·Oct 31Full Table, Incremental or CDC? What Each Ingestion Method Misses, From Databases to StreamsTake a subscriptions table with three users. In the first week of May, user 3 signs up, user 2 upgrades from trial to premium, and user 3…A response icon1A response icon1
Adam Chang·Oct 27The Six Layers of a Cloud Data Platform, and Why Apache Iceberg Became the Contract Between ThemA cloud data platform isn’t a product you buy. It’s six layers, each with one job, that only talk to each other through agreed formats and…A response icon1A response icon1
Adam Chang·Oct 25Four Late Rows Taught Me More About Apache Iceberg Than 70,272 Clean OnesLoading a year of clean weather data into Apache Iceberg took one command. The hard part of this side project was the second batch: four…
Adam Chang·Oct 24Data Warehouse vs Data Platform: Why Your Warehouse Shouldn’t Parse JSONA warehouse is the right place to answer questions. It is the wrong place to clean up after your data sources. That one distinction…A response icon1A response icon1
Adam Chang·Oct 1I Built a NYC Taxi Data Pipeline on Azure From Scratch: The Hardest Bug Wasn’t Code — It Was…A few months ago, I opened the Azure Portal for what was basically the first serious time in my career.
Adam Chang·Sep 17Every Bug That Mattered in My RAG System Failed SilentlyBuilding Agentic RAG with LangGraph, Pinecone and Tavily — and learning that the expensive failures never throw.
Adam Chang·Sep 17I Followed a LangGraph Tutorial. Then I Spent a Week Asking Why Every Decision Was Right.Building a multi-agent SQL system taught me less than auditing it did — including three bugs I only found while writing this article.