Capture AI application traces, evaluations, and prompts with OpenTelemetry.
npx skills add https://github.com/Arize-ai/phoenix --skill arize-phoenix
Please help me install this Agent Skill. Skill: arize-phoenix Source: https://github.com/Arize-ai/phoenix/tree/main/docs/phoenix Command: npx skills add https://github.com/Arize-ai/phoenix --skill arize-phoenix
Phoenix provides end-to-end observability for AI applications, enabling you to trace execution, evaluate outputs, and iterate on prompts in a single platform.
Get started by inspecting the Phoenix docs, instrumenting your application with OTLP, and running a simple trace in a local environment.
High-intent search queries and answers about installing and using this skill.
You can trace LLM calls, tool executions, retrievals, and embeddings by instrumenting your AI applications with OpenTelemetry. Phoenix captures these traces to provide end-to-end observability for debugging and optimizing production environments.
OpenInference is an instrumentation standard used alongside OpenTelemetry to capture AI application traces. It enables Phoenix to record execution paths, prompts, and retrievals, ensuring production-grade visibility for LLM-based systems.
Yes, you can run LLM-based or code-based evaluators to assess outputs and attach quality annotations directly to traces. This allows you to measure retrieval quality and iterate on prompts using data-driven signals.
You can iterate prompts, manage versions, and run experiments against datasets to compare prompt versions. This allows you to evaluate different configurations and optimize multi-turn agents within a single platform.
Yes, deploying Phoenix requires OpenTelemetry instrumentation and OpenInference where applicable. You can self-host the environment via Docker or Kubernetes, or alternatively use Phoenix Cloud for observability.
The best way to debug multi-turn agents is to capture end-to-end traces and run evaluations on retrieval quality. Phoenix enables this by recording execution paths and attaching evaluation signals to improve production AI apps.
AesopScottAnalyze traces, OpenInference, OpenTelemetry, datasets, and experiments with Phoenix in MAPS Phase 7.
Fluxloop-AICompare prompt versions by running repeated tests via the fluxloop CLI.
grafanaSend telemetry data to Grafana Cloud via Prometheus, OTLP, Loki, and Tempo.
aaronachermannInstruments Python and TypeScript apps with MLflow tracing for LLM calls and retrievals.
