> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://www.comet.com/docs/opik/tracing/llms.txt.

# Observability

> Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

## Docs

- [Observability Overview](https://www.comet.com/docs/opik/tracing/overview.md): Monitor, debug, and optimize your LLM applications with Opik's observability platform for traces, spans, and conversations
- [Getting started with Observability](https://www.comet.com/docs/opik/tracing/getting-started.md): Add observability to your LLM application with Opik tracing using AI-powered skills or manual SDK integration
- [Tracing Core Concepts](https://www.comet.com/docs/opik/tracing/concepts.md): Learn about the core concepts of Opik's tracing system, including traces, spans, and threads, and how they work together to provide comprehensive observability for your LLM applications.
- [Debugging agents with Ollie](https://www.comet.com/docs/opik/tracing/debug-agents.md): Use Ollie and Opik Connect to investigate failing traces, identify root causes in your code, and verify fixes with test suites — all from the Opik dashboard
- [Diagnostics](https://www.comet.com/docs/opik/tracing/diagnostics.md): Opik Diagnostics automatically scans your project's traces with Ollie and surfaces recurring agent issues, complete with root cause, a suggested fix, and affected traces.
- [Log traces](https://www.comet.com/docs/opik/tracing/advanced/log_traces.md): Monitor the flow of your LLM applications with tracing to identify issues and optimize performance using Opik's powerful tools.
- [Log conversations](https://www.comet.com/docs/opik/tracing/advanced/log_chat_conversations.md): Capture and analyze chat conversations on Opik, enabling better tracking of user interactions and improving chatbot performance.
- [Log media & attachments](https://www.comet.com/docs/opik/tracing/advanced/log_multimodal_traces.md): Capture multimodal traces in Opik by logging images, videos, and audio files using the Python SDK's Attachment type.
- [Log Agent Graphs](https://www.comet.com/docs/opik/tracing/advanced/log_agent_graphs.md): Learn to log agent execution graphs in Opik for enhanced debugging and flow visualization across frameworks like LangGraph and Google ADK.
- [Log distributed traces](https://www.comet.com/docs/opik/tracing/advanced/log_distributed_traces.md): Learn to track distributed traces in complex LLM applications using Opik's built-in support for multi-service tracing.
- [Log user feedback](https://www.comet.com/docs/opik/tracing/advanced/annotate_traces.md): Capture user feedback and track performance metrics to enhance your agent's effectiveness with Opik's logging capabilities.
- [Cost tracking](https://www.comet.com/docs/opik/tracing/advanced/cost_tracking.md): Monitor and analyze cost patterns in your LLM apps using Opik's dashboard to identify anomalies and optimize spending.
- [Export data](https://www.comet.com/docs/opik/tracing/advanced/export-data.md): Export traces, spans, threads, datasets, and experiments from Opik using the SDK, REST API, UI, or command-line tools
- [Migrate data](https://www.comet.com/docs/opik/tracing/advanced/migrate-data.md): Move datasets and prompts — with their full version history and attached data — between projects with the opik migrate CLI command.
- [SDK configuration](https://www.comet.com/docs/opik/tracing/advanced/sdk_configuration.md): Configure Python and TypeScript SDKs effectively. Set up your API key and instance URL for seamless routing and authentication.
- [Offline fallback and message replay](https://www.comet.com/docs/opik/tracing/advanced/offline_fallback.md): Keep your tracing data intact during network outages with Opik's offline fallback. Learn how failed messages are automatically stored and replayed when connectivity is restored.
- [Dashboards](https://www.comet.com/docs/opik/tracing/dashboards/dashboards.md): Create customizable dashboards to monitor quality, cost, and performance of your LLM projects and visualize experiment results.
- [Production monitoring](https://www.comet.com/docs/opik/tracing/dashboards/production_monitoring.md): Monitor your production LLM applications with Opik. Evaluate feedback scores, trace counts, and token usage daily and hourly for optimal insights.