Writing
Notes on building AI products
Lessons from taking AI from prototype to production — engineering, architecture, and the decisions that decide whether an AI feature ships.
RAG vs fine-tuning for SMEs
Small and mid-sized companies rarely need a fine-tuned model. Retrieval is cheaper, faster to ship, and easier to keep correct. Here is the trade-off.
When to build an agent vs a workflow
Agents are powerful, but most production AI features are better served by a deterministic workflow. Here is how we decide.
Shipping AI that survives production
Demos are easy. The gap between a convincing prototype and a reliable product is where most AI projects stall.