Alexey ban·Oct 26From Legacy ERP Source to a Reconciled LakehouseHow I pointed EKOS at an open-source Java ERP, taught it Java and Oracle, let it document the system, and had it generate a bronze and…
Alexey ban·Oct 12Three Questions Every Enterprise AI Team Should Ask — Answered from the EKOS CodebaseAn LLM in EKOS never decides anything on its own authority. Here is how the code makes that true — with the parts that still fall short.
Alexey ban·Aug 27Facts, Not Documents: Why I Built a Knowledge Compiler That Refuses to GuessWhat I learned building a knowledge compiler in Rust, and why “I don’t know” is a feature
Alexey ban·Jun 26Asking a Data Warehouse Questions in Plain English: An Honest Look at a Semantic Vault on…Part 3 of an engineering diary about building a dvdrental data platform on Azure and Databricks. The earlier parts covered the medallion…
Alexey ban·Jun 23Metadata-Driven Azure Data Platform with Azure Data Factory, Databricks, and dbtA technical case study: how one JSON config file governs fifteen tables, three processing layers, and a complete medallion lakehouse —…
Alexey ban·Jun 20Building an Azure Data Platform in One Week with Claude CodeAn engineering case study, not a product pitch: what an AI pair programmer actually did, and didn’t do, on a real three-repo data platform…
Alexey ban·Jun 12Inside Spark’s Catalyst Optimizer: How Your Lazy SQL Becomes Fast CodeYou write a five-line query. Spark turns it into something dramatically faster than what you literally asked for. Here’s the machinery that…
Alexey ban·Apr 17What It Actually Takes to Build a Private AI Assistant for Your BusinessA client came to me with a brief that went something like this:
Alexey ban·Mar 15I Let an AI Build a Full Data Engineering Platform From Scratch. Here’s What Actually Happened.15 sessions. ~16 hours. 2 free AI models. Zero human-written code. MIT License.