Confident AI OpenTelemetry Export

Use this skill to instrument an AI application—an LLM app, agent, RAG pipeline, or chatbot—with raw OpenTelemetry so its traces land in Confident AI. No confident-trace package is needed. The job is exactly two things: export to the correct Confident AI OTLP endpoint and set the confident.* attributes Confident AI reads from each span.

Scope: AI Applications Only

Instrument only agent loops and planning, LLM calls, retrieval/vector search, and tool calls. Do not apply confident.* attributes to web servers, CRUD backends, database layers, infrastructure, or non-AI spans. If the target has no LLM, agent, retrieval, or tool-calling component, this skill does not apply.

When to Use vs the Other Skills