Sentry Setup Ai Monitoring

This sets up Sentry's AI monitoring so you can track LLM calls, token usage, and agent execution across OpenAI, Anthropic, Vercel AI, LangChain, and others. It detects what AI SDKs you've already installed, configures the right integrations, and handles the tricky part about sampling rates (AI traces need to be sampled as complete trees or you lose visibility). The skill is opinionated about PII: it won't enable prompt and output recording without asking you first, which is smart since you're basically capturing user conversations. Works for both JavaScript and Python, with auto-instrumentation where available and manual span setup when you need it. Good if you want observability without reading through Sentry's docs to figure out which integration matches your stack.

skills.sh installs: 3K
GitHub stars: 277
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add getsentry/sentry-for-ai --skill sentry-setup-ai-monitoring --agent claude-code

Installs into .claude/skills of the current project.

Files

All Skills > Feature Setup > AI Monitoring

Setup Sentry AI Agent Monitoring

Configure Sentry to track LLM calls, agent executions, tool usage, and token consumption.

Invoke This Skill When

User asks to "monitor AI/LLM calls" or "track OpenAI/Anthropic usage"
User wants "AI observability" or "agent monitoring"
User asks about token usage, model latency, or AI costs

Important: The SDK versions, API names, and code samples below are examples. Always verify against docs.sentry.io before implementing, as APIs and minimum versions may have changed.

Prerequisites

AI monitoring requires tracing enabled (tracesSampleRate > 0).

If the app has multi-turn chats, set a conversation ID by default anywhere it makes sense to identify a chat session. Sentry uses gen_ai.conversation.id to group related AI spans into Conversations. Some integrations infer it automatically, but many setups need to set it explicitly.