> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/guardrails/v0.24.0/observability/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/guardrails/_mcp/server.

# Observability

## Docs

- [Observability Overview](https://docs.nvidia.com/nemo/guardrails/v0.24.0/observability/observability.md): Logging, tracing, and metrics for end-to-end visibility into the behavior of the NVIDIA NeMo Guardrails library.
- [Logging and Debugging Guardrails Generated Responses](https://docs.nvidia.com/nemo/guardrails/v0.24.0/observability/logging.md): Debug guardrails with verbose mode, explain method, and generation log options.
- [Tracing Guardrails](https://docs.nvidia.com/nemo/guardrails/v0.24.0/observability/tracing.md): Enable distributed tracing with OpenTelemetry to monitor guardrails execution and LLM calls.
- [Quick Start for Tracing Guardrails](https://docs.nvidia.com/nemo/guardrails/v0.24.0/observability/tracing/quick-start.md): Set up tracing in minutes with the OpenTelemetry SDK and console output.
- [Adapter Configurations](https://docs.nvidia.com/nemo/guardrails/v0.24.0/observability/tracing/adapter-configurations.md): Configure FileSystem, OpenTelemetry, or custom adapters for guardrails tracing.
- [OpenTelemetry Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.0/observability/tracing/opentelemetry-integration.md): Configure OpenTelemetry SDK with OTLP exporters for production monitoring backends.
- [Exporting Guardrails Logs to OpenTelemetry](https://docs.nvidia.com/nemo/guardrails/v0.24.0/observability/tracing/opentelemetry-logs.md): Forward Python logs from the NeMo Guardrails library into your OpenTelemetry backend with automatic trace correlation.
- [Span Reference](https://docs.nvidia.com/nemo/guardrails/v0.24.0/observability/tracing/span-reference.md): Reference the LLMRails, IORails, and canonical outbound HTTP spans and attributes emitted when tracing is enabled.
- [Capturing Prompt and Response Content](https://docs.nvidia.com/nemo/guardrails/v0.24.0/observability/tracing/content-capture.md): Record prompt and response content on tracing spans, including the environment variables that control capture and output format.
- [Troubleshooting](https://docs.nvidia.com/nemo/guardrails/v0.24.0/observability/tracing/troubleshooting.md): Resolve common tracing issues with OpenTelemetry SDK configuration and connectivity.
- [Metrics for Guardrails](https://docs.nvidia.com/nemo/guardrails/v0.24.0/observability/metrics.md): Emit OpenTelemetry metrics from the opt-in IORails engine for SLO dashboards, capacity planning, and LLM cost tracking.
- [Enable Guardrails Metrics](https://docs.nvidia.com/nemo/guardrails/v0.24.0/observability/metrics/enable-metrics.md): Set up metrics in minutes with the OpenTelemetry SDK and console output.
- [OpenTelemetry Metrics Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.0/observability/metrics/opentelemetry-integration.md): Configure the OpenTelemetry SDK with OTLP and Prometheus exporters for production metrics backends.
- [Metric Reference](https://docs.nvidia.com/nemo/guardrails/v0.24.0/observability/metrics/reference.md): Reference IORails and canonical outbound HTTP metrics, including instrument types, units, labels, and emission semantics.