Observing Traces and Metrics

The Observability Dashboard provides visibility into your protected agents, showing guardrail activity, latency metrics, and execution traces.

​

Accessing Telemetry

1. Navigate to Guardrails in the sidebar
2. Find your agent in the Registered Agents table
3. Click the Monitor icon (chart) in the Monitor column

The telemetry dashboard opens for that agent.

​

Dashboard Layout

The dashboard has three main sections:

​

Guardrail Metrics

Summary cards at the top show aggregate statistics: Input Guardrails:

• Flagged Requests — Number and percentage of requests that triggered input guards
• Errors — Count of processing errors in input guards

Output Guardrails:

• Flagged Responses — Number and percentage of responses that triggered output guards
• Errors — Count of processing errors in output guards

​

Time Series Charts

Four charts visualize guardrail activity over time:

​

Execution Traces & Logs

Real-time monitoring of individual guardrail executions: Traces — Detailed execution logs for each request, showing:

• Request ID
• Guards executed
• Detection results
• Timing information

Logs — Streaming log output with search and level filtering.

​

Dashboard Controls

​

Layout Options

Toggle between:

• Grid — Charts arranged in a grid layout
• Row — Charts stacked vertically

​

Chart Type

Select how data points are displayed:

• Line Connected — Points connected with lines
• Line Gaps — Lines with gaps for missing data
• Points Only — Individual data points without connecting lines

​

Time Range

Filter data by time period:

• Last 24 Hours
• Last 7 Days
• Last 30 Days
• Custom range

All times display in UTC.

​

Reading the Charts

​

Flagged Requests/Responses

The bar charts show two series:

• Red bars — Requests/responses flagged by guardrails
• Dark bars — Total requests/responses

Hover over any bar to see exact counts and timestamps. A high flag rate may indicate:

• Active threats being blocked
• Overly sensitive guard configuration (false positives)
• User behavior patterns that need attention

​

Latency Distribution

The latency charts show percentile lines:

• P50 (Median) — Half of requests complete faster than this
• P90 — 90% of requests complete faster than this
• P95 — 95% of requests complete faster than this
• P99 — 99% of requests complete faster than this

Monitor P99 latency to understand worst-case user experience. Spikes in P99 may indicate:

• Guard processing bottlenecks
• Resource contention
• Complex inputs requiring more analysis

​

Execution Traces

The Traces panel shows recent guardrail executions. Click any trace to view:

• Request ID — Unique identifier for the request
• Timestamp — When the request was processed
• Guards Executed — Which guards ran and in what order
• Detection Results — Whether each guard flagged the content
• Timing Breakdown — How long each guard took

Use traces to debug:

• Why specific requests were flagged
• Which guards are slowest
• How guards interact in your pipeline

​

Logs Panel

The Logs panel shows streaming log output from your guardrails.

​

Filtering Logs

Filter by log level:

• All Levels — Show everything
• Error — Only errors
• Warning — Warnings and above
• Info — Informational and above
• Debug — All log levels

Use the search box to find logs containing specific text.

​

Real-time Updates

Toggle Real-time Updates to enable or disable automatic log streaming. Disable when you need to examine a specific log entry without the view scrolling.

​

Interpreting Metrics

​

Healthy Patterns

• Low flag rate (< 5%) with consistent traffic
• Stable latency without significant P99 spikes
• Few errors in guardrail processing

​

Warning Signs

​

Exporting Data

Use telemetry data for:

• Compliance reporting
• Security audits
• Performance analysis

Export options are available through the API. See Developer Guide > API Reference for details.

​

Next Steps