# What is Phoenix? Definition and meaning

A tool for tracing LLM applications with OpenTelemetry and running evaluations on the traces.

## Definition

**Phoenix**: A tool for tracing LLM applications with OpenTelemetry and running evaluations on the traces.

In short: Open-source tracing and evaluation from Arize.

## When it is used

Inspecting and evaluating RAG pipelines and agents.

## Where it fits

Phoenix belongs to **LLM observability and evaluation** in the [Generative AI and LLMs](/topics/generative-ai-llms) topic. These are the other terms in the same group:

- **[LangSmith](/glossary/langsmith)**: A platform from LangChain for tracing runs, building datasets and evaluating prompts and agents.
- **[Langfuse](/glossary/langfuse)**: A platform for tracing, prompt management, scoring and cost tracking of LLM applications.
- **[Braintrust](/glossary/braintrust)**: A platform for running experiments, scoring outputs and tracking quality over time.
- **[PromptFoo](/glossary/promptfoo)**: A command-line tool that runs test cases and comparisons across prompts and models, including security tests.
- **[lm-evaluation-harness](/glossary/lm-evaluation-harness)**: EleutherAI's framework that runs a large library of academic benchmarks against a model with a unified interface.

## Learn more

The full guide to **[Phoenix](/tools/phoenix)** explains how it works, when to use it and how it compares with the alternatives, with examples. The [glossary](/glossary) lists every term on the site from A to Z.

Previous term: [pgvector](/glossary/pgvector) · Next term: [Pinecone](/glossary/pinecone)
