Phoenix
Phoenix Arize is an open-source AI observability platform for LLMs.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Phoenix, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
Phoenix Arize is an open-source AI observability platform designed to trace, evaluate, and optimize language model (LLM) applications. Built on OpenTelemetry, it is vendor, framework, and language agnostic, providing flexibility and comprehensive visibility into the inner workings of AI applications. It supports pre-deployment evaluation and troubleshooting directly from a local machine, making it ideal for early-stage developers.
Key features and capabilities
- Performance tracing, dashboards, LLM evaluation library, span-level visibility, prompt playground.
Use cases
- Troubleshooting LLM applications, optimizing prompt templates, reducing hallucinations, evaluating RAG relevance, monitoring AI performance.