LLM calls are black boxes in production. Learn how to add structured observability to your RubyLLM-powered app with OpenTelemetry.

Thoughtbot's platform is a central hub for software developers and product designers, offering insights into product development, design thinking, and agile methodologies. Through articles, case studies, and design sprints, Thoughtbot offers insights into user research, prototyping, and usability testing. Readers can learn about lean product development, iterative design processes, and cross-functional collaboration to create user-centric digital products and services.

thoughbot

Adding structured observability to RubyLLM-powered applications using OpenTelemetry is now possible with a new gem released by Thoughtbot. The opentelemetry-instrumentation-ruby_llm gem automatically captures traces for chat completions, tool calls, and token usage following OpenTelemetry GenAI semantic conventions. Setup requires adding three gems and a single initializer — no manual trace wrapping needed. Traces can be exported to any OTLP-compatible backend, including Langfuse, providing latency timelines, cost tracking, tool call details, and full audit trails. This is especially valuable for regulated industries requiring visibility into AI behavior in production.

Observability for your LLM-powered apps: OTel Instrumentation for RubyLLM

OpenTelemetry instrumentation for RubyLLM

If you enjoyed this post, you might also like: