Here you will find all my articles published on Medium. I write regularly about Semantic Layers, Postgres, LLM Evaluation, CDC Pipelines, and Stream Processing.
To build reliable Text-to-SQL agents, your semantic layer needs a Schema Routing Engine . Here is how it works, what we learned testing it in real benchmarks, and the best practices for implementin...
A deep dive into the disk architectures of RocksDB/Flink and PostgreSQL, how memory access patterns shape I/O trade-offs, and when to use each. As software engineers or Data Engineers, we often tre...
Read a real routing config, run it against a live agent, then deliberately revert one function to its old, buggy version and watch a real misrouting bug come back on your own machine. My previous p...
A weekly merge job kept getting slower, week after week. Every signal pointed at the usual suspect. It wasn’t. Here’s how we told the difference, and what was actually eating the extra time. A few ...
Building a Semantic Layer from Zero (Part 2): Can Column Descriptions Alone Stop an LLM From Hallucinating SQL? Same 6 questions, same database — but this time the model gets the schema. 6/6 correc...
6 questions, 12 attempts, 1 silent fabrication that would have gone straight into a report This is part 1 of a 6-post series that answers one question: How much context does a model actually need t...
8 architecture decisions, 5 Debezium incidents, 3 corrections — and what a streaming pricing engine looks like after all of them The entire project was built with spec-driven development — every ph...
Hash tables, sorting algorithms, and Big-O explain joins and shuffle issues better than any tuning guide Apache Spark didn’t invent any new data structure or algorithm , it just the reused the clas...
I was building a streaming pricing engine for vacation rental apartments. The system ingests operational costs via CDC from PostgreSQL through Debezium into Kafka, market reference prices through K...
There’s a pattern that works really well for building data lakes on AWS: Kinesis captures events, Lambda processes them, S3 stores them, Glue transforms them, Athena queries them. It’s cheap, it sc...