Skill UI

Guides writing idiomatic Elixir code with OTP patterns, supervision trees, Phoenix LiveView, Ecto, concurrency, distributed systems, and BEAM performance tuning while insisting on best practices, actionable checks, and validation steps for resilient services.

Phoenix is an open-source observability platform for tracing, evaluating, and monitoring LLM applications; use it to debug prompts, run dataset evaluations, build experiment pipelines, and watch production inference in real time.

Phoenix CLI streamlines debugging Phoenix-based LLM observability: it fetches traces, spans, sessions, datasets, experiments, prompts, and GraphQL data while piping JSON to tools like jq so you can triage errors, inspect performance, and verify deployments quickly.

Phoenix Evals lets teams build evaluators for AI/LLM apps by wiring deterministic code with LLM nuance, running Python or TypeScript workloads, validating against humans, and iterating through error analysis, RAG, and production workflows.

Guides hooking Phoenix AI services with OpenInference tracing, covering setup, spans, instrumentation, and production deployment for LLM workflows using Python or TypeScript.