Why Observability? Defense without observability is flying blind. You need to know what’s happening with your protected agents, not just that guardrails are running, but what they’re catching, how often, and what patterns are emerging.
Dome includes built-in telemetry that captures the full picture of agent behavior in production. This data serves three purposes:
Operational visibility : Are your guardrails working? What’s getting blocked? What’s the latency impact?Security monitoring : Are you seeing attack patterns? Anomalous behavior? Escalating threats?Continuous improvement : What’s happening in production that evaluation didn’t anticipate?
Telemetry Dome automatically captures telemetry from every protected interaction. When instrumented by the developer, this includes:
Execution Traces Full traces of LLM and tool execution:
{ "trace_id" : "abc123" , "timestamp" : "2024-01-15T10:30:00Z" , "agent_id" : "support-bot-v2" , "spans" : [ { "name" : "input_guardrail" , "duration_ms" : 23 , "guards_executed" : [ "prompt-injection" , "pii-detection" ], "result" : "pass" }, { "name" : "llm_call" , "model" : "gpt-4" , "duration_ms" : 1250 , "tokens" : { "input" : 450 , "output" : 230 } }, { "name" : "tool_call" , "tool" : "search_knowledge_base" , "duration_ms" : 89 , "result" : "success" }, { "name" : "output_guardrail" , "duration_ms" : 18 , "guards_executed" : [ "toxicity" , "pii-redaction" ], "result" : "pass" } ] }
Traces let you see exactly what happened in each interaction—which guards ran, what the LLM did, which tools were called, and how long each step took.
Instrumentation To capture full traces, instrument your agent with Dome’s SDK:
from vijil.dome import DomeClient, trace dome = DomeClient() @trace ( "my-agent" ) async def handle_request ( user_input : str ): # Input guardrail (automatic) filtered_input = await dome.scan_input(user_input) # LLM call (traced) with trace.span( "llm_call" ): response = await llm.generate(filtered_input) # Tool calls (traced) with trace.span( "tool_call" , tool = "search" ): results = await search_tool(response.query) # Output guardrail (automatic) filtered_output = await dome.scan_output(response.text) return filtered_output
Guardrail spans are captured automatically. LLM and tool spans require explicit instrumentation but provide complete visibility into agent behavior.
Metrics Dome aggregates telemetry into operational metrics:
Protection Metrics Metric Description inputs_scannedTotal inputs processed by input guardrails inputs_blockedInputs blocked by guards inputs_redactedInputs modified by redaction guards outputs_scannedTotal outputs processed by output guardrails outputs_blockedOutputs blocked by guards outputs_redactedOutputs modified by redaction guards block_ratePercentage of interactions blocked
Latency Metrics Metric Description input_guardrail_p50Median input guardrail latency input_guardrail_p9999th percentile input guardrail latency output_guardrail_p50Median output guardrail latency output_guardrail_p9999th percentile output guardrail latency total_overhead_msTotal latency added by Dome
Guard-Level Metrics Metric Description guard.{name}.triggersHow often this guard triggers guard.{name}.confidence_avgAverage confidence when triggered guard.{name}.latency_p50Median guard execution time
Metrics are available via API, dashboard, and can be exported to your observability stack (Datadog, Prometheus, etc.).
Logs Dome generates structured logs for every significant event:
Detection Logs When a guard detects a threat:
{ "level" : "warn" , "event" : "guard_triggered" , "timestamp" : "2024-01-15T10:30:00Z" , "agent_id" : "support-bot-v2" , "guard" : "prompt-injection" , "action" : "block" , "confidence" : 0.94 , "input_hash" : "sha256:abc..." , "evidence" : "Detected instruction override pattern" }
Audit Logs For compliance and security review:
{ "level" : "info" , "event" : "interaction_complete" , "timestamp" : "2024-01-15T10:30:02Z" , "agent_id" : "support-bot-v2" , "session_id" : "sess_xyz" , "input_guardrail" : { "result" : "pass" , "duration_ms" : 23 }, "output_guardrail" : { "result" : "redact" , "duration_ms" : 18 , "guard" : "pii" }, "total_duration_ms" : 1380 }
Logs can be shipped to your SIEM, log aggregator, or stored in Vijil for analysis.
Dashboard The Dome dashboard provides real-time visibility:
Overview : Block rates, latency, active agentsGuard performance : Which guards are triggering, at what ratesThreat timeline : Detection events over timeDrill-down : From metric to trace to individual interaction
Next Steps
Observe Traces Monitor guardrail performance
How Defense Works The defense architecture
Last modified on April 20, 2026
