CARMINE PAOLINO

RubyLLM 1.x gave Rubyists a beautiful way to work with AI: one delightful DSL across major providers, easy Rails integration, a model registry for capabilities and costs, instrumentation, agents, workflows, and RAG. But in production a new set of problems appears — calls get expensive, providers have bad days, answers need provenance, and workflows need tracing. RubyLLM 2.0 crosses that line: caching and batch execution to cut costs, model fallbacks to keep answering, citations so users can see where answers came from, and workflow-aware tracing to understand complex flows. It also separates providers from protocols, so multi-protocol providers work natively and smaller providers can be added with a simple generator.

Carmine builds the tools he wants to use, in Ruby and Rails. He created RubyLLM to make production AI features feel natural in Rails, and founded Chat with Work. In a previous life he spent a decade as a machine learning scientist and engineer, mostly in Python.