phoenix▌

Comprehensive guide for instrumenting LLM applications with OpenInference tracing in Phoenix. Contains reference files covering setup, instrumentation, span types, and production deployment.

Build evaluators for AI/LLM applications. Code first, LLM for nuance, validate against humans.

The CLI uses singular resource commands with subcommands like list and get:

Phoenix builds on Elixir and the BEAM VM to deliver fault-tolerant, real-time web applications with minimal JavaScript. LiveView keeps UI state on the server while streaming HTML diffs over WebSockets. The BEAM provides lightweight processes, supervision trees, hot code upgrades, and soft-realtime scheduling.

Open-source AI observability and evaluation platform for LLM applications with tracing, evaluation, datasets, experiments, and real-time monitoring.