Writing

Technical Insights.

Deep-dives on AI engineering, production ML, and the systems I build. Written for engineers, by an engineer.

Featured

NL to SQL: Handling Complex Relational Schemas with LLMs

The hardest part of building a Natural Language to SQL (NL-to-SQL) system isn't the language model — it's reliably conveying the schema to the model without hitting context limits or leaking sensitive data.

8 min read

Read Article

All Articles

LLMObservabilityClickHouse

Real-Time Observability for Large Language Models (LLMs)

Running an LLM in production without observability is like flying a plane with no instruments. Here's the architecture I built to give AI teams full visibility and real-time observability for large language models.

9 min read

RAGLlama 3.3Groq

Building a Sub-100ms RAG Engine with Llama 3.3 and Groq

Most Retrieval-Augmented Generation (RAG) implementations treat retrieval as an afterthought. I spent three months obsessing over it. Here's what I learned about building retrieval that is fast enough to feel native.

11 min read