Summary
This is your complete reference for instrumenting LLM apps with Phoenix's OpenInference tracing. It covers both Python and TypeScript, walking you through auto-instrumentation for popular frameworks like OpenAI and LangChain, plus manual span creation when you need fine-grained control. The real value is in the nine span type specs (LLM, chain, retriever, tool, agent, etc.) with full attribute schemas, so you know exactly what metadata to attach. Production patterns for batching and PII masking are here too. If you're shipping an LLM app and need observability beyond print statements, this gives you the complete OpenInference implementation without hunting through docs.
Install to Claude Code
npx -y skills add github/awesome-copilot --skill phoenix-tracing --agent claude-codeInstalls into .claude/skills of the current project.
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →Files
SKILL.md
Select a file.
Featured
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →
