Agentforce observability — preview traces and sf agent trace, the trace step types, Apex debug in preview, enhanced event logs, Session Tracing in Data 360 with its data model, and the OpenTelemetry export API
Where to see what an Agentforce agent did. In development, preview writes a trace per turn that `sf agent trace` reads by dimension (actions, grounding, routing, errors). In production, Session Tracing stores sessions, turns, steps, LLM prompts and quality scores in Data 360 objects, and a beta API exports one session as OpenTelemetry. Covers what to turn on in Setup, what each source holds, and the limits.
markdownreferencev2CKRV-D4MFstage: operatetrust: officialservice: agentforceinterface: cliinterface: restinterface: data-360agent observabilitysf agent trace listsf agent trace readsf agent trace delete--format summary detail raw--dimension actions grounding routing errorstrace files .sfdx/agentsplanIdNodeEntryStateStepEnabledToolsStepReasoningStepPlannerResponseStepVariableUpdateStepsafety scorepreview transcripts--apex-debug Replay Debuggerenable_enhanced_event_logs--enrich-logsAgentforce Session TracingEinstein Audit, Analytics, and Monitoring SetupAudit and FeedbackAiAgentSessionAiAgentInteractionAiAgentInteractionStepAiAgentMomentAiAgentTagAssociation quality scoreGenAIGeneration__dlmGenAIGatewayRequest__dlmTOPIC_STEP LLM_STEP ACTION_STEP TRUST_GUARDRAILS_STEPOpenTelemetry export/einstein/audit/otel72 hoursAgent Health Monitoring
Agent observability
| Question | Look at |
|---|---|
| Why did my draft agent pick that subagent or action? | Preview traces, read with sf agent trace |
| Why did my Apex action fail inside the agent? | Live preview with --apex-debug, then the Apex Replay Debugger |
| What happened in production yesterday? | Session Tracing in Data 360 |
| Does my agent still pass after a change? | Agent tests (reference/agentforce/agent-testing.md) |
Preview traces (development)
Every sf agent preview turn records a trace in the project: .sfdx/agents/<agent>/sessions/<sessionId>/traces/<planId>.json, per Salesforce's sf-skills. Keep .sfdx/ out of git. Transcripts save to ./temp/agent-preview (--output-dir changes it).
sf agent trace list --agent Steward_Agent --since 2026-10-23
sf agent trace read --session-id <id> # per-turn summary
sf agent trace read --session-id <id> --format detail --dimension actions --turn 2
sf agent trace read --session-id <id> --format raw # the JSON, for your own analysis
sf agent trace delete --older-than 7d --no-prompt--dimension (with --format detail) | Shows |
|---|---|
actions | Each action run: name, inputs, output, latency |
grounding | The LLM's reasoning steps |
routing | Moves between subagents, and why |
errors | Every error in the session |
Raw trace steps (the plan[] array), per sf-skills:
| Step type | Holds |
|---|---|
NodeEntryStateStep | The subagent entered |
EnabledToolsStep | Which tools were visible (check available when) |
BeforeReasoningIterationStep | The actions about to run |
ReasoningStep | Grounding category and reason |
VariableUpdateStep | Each variable's old value, new value and why it changed |
PlannerResponseStep | The reply, with its safety score |
If parsing fails, the trace schema may have changed: "Try "--format raw" to access unprocessed trace data."
--apex-debug on sf agent preview captures Apex debug logs during a live preview. Replay them in VS Code with the Apex Replay Debugger.
Production: Session Tracing in Data 360
Turn it on: in Setup, search for Einstein Generative AI, open Einstein Audit, Analytics, and Monitoring Setup, and turn on Agentforce Session Tracing and Audit and Feedback. Data 360 must be provisioned. Sessions are then stored in the Session Trace Data Model, queryable with Data 360 SQL (reference/data360/object-model-and-apis.md).
Object (ssot__<Name>__dlm) | One row per | Useful fields |
|---|---|---|
AiAgentSession | Conversation | start and end, channel, end type, final variables |
AiAgentSessionParticipant | Agent or user in it | AiAgentApiName (filter on this) |
AiAgentInteraction | Turn | TopicApiName (the subagent), timings, telemetry trace ID |
AiAgentInteractionMessage | Message | Input or Output, text |
AiAgentInteractionStep | Step | type (TOPIC_STEP, LLM_STEP, ACTION_STEP, TRUST_GUARDRAILS_STEP, SESSION_END), name, input, output, error, variables before and after |
AiAgentMoment + AiAgentTagAssociation → AiAgentTag | User intent | LLM summaries of request and response, a 1–5 quality score with its reasoning |
The full prompt and response of each LLM step are in GenAIGatewayRequest__dlm.prompt__c and GenAIGeneration__dlm.responseText__c. They are joined on the step's gateway request and generation IDs, and filled only when Audit and Feedback is on. They can contain customer data, so treat access to them like access to the conversations.
Export one session as OpenTelemetry (beta):
GET /services/data/v66.0/einstein/audit/otel/{session-id}with an OAuth token from an External Client App returns OTLPResourceSpans.- Only sessions that started in the last 72 hours are available, and only one session per request.
- Salesforce Connect API rate limits apply.
Event logs: enable_enhanced_event_logs: True in the Agent Script config block, or --enrich-logs true on sf agent generate agent-spec, adds conversation data to the agent's event logs.
Alerts: Salesforce's agentforce-observe skill also manages Agent Health Monitoring alerts. The hub hasn't verified that API.