9.1 Managing and Monitoring Agents

Key Takeaways

  • Agentforce observability has three layers: infrastructure that captures telemetry, build-and-test tools, and observe tools for production monitoring.
  • Agentforce Session Tracing captures turns, reasoning steps, actions, prompt and gateway inputs and outputs, errors, and responses, and it must be enabled before other observability tools have data.
  • Agent Health Monitoring sends email alerts when metrics such as error rate, interaction latency, escalation rate, or response rate breach thresholds.
  • Monitor Agent Guardrails tracks instruction adherence and task resolution trends separately from broader analytics.
  • Users with Manage AI Agents can manage, activate, deactivate, and monitor all agents org-wide, so assign it only to those who need that access.
Last updated: September 2026

9.1 Managing and Monitoring Agents

Quick Answer: Managing agents covers who can build and change them (Manage AI Agents, Service agent managers), who can use them (Employee agent access), and what version is live (draft, commit, activate, deactivate). Monitoring relies on a layered observability toolchain: Agentforce Session Tracing and audit and feedback data capture telemetry, then Agent Analytics, Agent Optimization, session traces, Agent Health Monitoring alerts, and guardrail monitoring show how agents perform in production.

Managing Agents: Access and Lifecycle Controls

ControlWhat it governsKey detail
Manage AI Agents permissionAccess to Agentforce Builder and management of agentsOrg-wide. Users can manage, activate, deactivate, customize subagents and actions, and monitor all agents
Manage Agentforce Service Agents permission setCreating and editing Service agentsIncludes Manage AI Agents. Admins can assign it to define Service agent managers
Agent Access (Employee agents)Which employees can use an agentPermission sets or profiles on the Agent Access page or in Enabled Agent Access
Agent user (Service agents)What data Service agents can reachLeast-privilege permissions; only admins can view or edit agent users
VersionsWhat's liveDraft → commitactivate. Compare versions, create drafts from committed versions, delete versions (not recoverable)
Activate / DeactivateAvailability on connected channelsActivating makes the agent immediately available to users on its channels
Model provider accessWhich LLM providers can be usedEinstein Setup → Configure Model Providers (section 5.4)
Audit and feedback dataRecord of prompts, responses, and trust signalsStored in Data 360 (section 5.3)

Good governance practice: build in sandboxes, test with Testing Center, deploy through a pipeline, keep the previous committed version for rollback, and restrict management permissions to a small group.

The Observability Toolchain

Salesforce describes observability as a layered toolchain, not a single tool.

Layer 1: Infrastructure (turn these on first)

ToolWhereWhat it captures
Agentforce Session TracingSetup → Agentforce Session TracingEvery turn, reasoning step, action, and message for every session. Must be enabled before other observability tools have data
Agent Platform TracingEinstein Audit, Analytics, and Monitoring SetupService-level telemetry across the Atlas reasoning engine, Apex, Flows, Prompt Builder, invocable actions, AI Gateway, LLM Gateway, and query federation
Audit and FeedbackEinstein Audit, Analytics, and Monitoring SetupLLM inputs and outputs, retrieval quality data, trust evaluations, guardrail outputs, user feedback. Powers quality and trust metrics
Knowledge/RAG Quality Data and MetricsSame Setup pageRetrieval scores such as answer faithfulness, answer relevance, and context relevance
Einstein Trust LayerEinstein Trust Layer SetupInstruction adherence and toxicity scores from LLM Gateway outputs

Layer 2: Build and Test

ToolPurpose
Agentforce Builder (Simulate and Live Test)Iterative testing
Interaction SummarySubagent selection, actions, and reasoning for a test conversation
Testing CenterBatch evaluation before deployment. Custom scorers later surface in Agent Analytics

Layer 3: Observe (production)

ToolPurpose
Agent AnalyticsAggregated trends across sessions in Tableau Next dashboards (section 9.2)
Agent OptimizationSession-level review with intents, outcomes, and quality scores (section 9.2)
Interaction Summary and TracePer-session breakdown and a time-ordered step record with timing and errors
Agent Health MonitoringAlerts on operational metrics
Monitor Agent GuardrailsInstruction adherence and task resolution trends
Omni Supervisor – Agentforce tabNear-real-time view of active voice calls with live transcripts
Data 360 Query EditorSQL over the underlying data for custom analysis

The toolchain works best in sequence: make sure infrastructure data is flowing, catch issues in build and test, then track and investigate in production.

Agentforce Session Tracing

Session tracing combines data from sources such as reasoning engine logs under a session ID. It supports all agent types, and you can query it through DMOs and reports. Use it to:

  • Debug configuration issues at build time
  • Learn why certain batch test cases failed
  • Explain why an agent can't handle a set of questions or goes off topic

Key Session Tracing Data Model (STDM) objects:

DMOContains
AiAgentSessionDmoSession facts: channel type, how the session ended, related messaging or voice session IDs
AiAgentSessionParticipantDmoWho joined: contact, lead, user, agent API name
AiAgentInteractionDmoOne turn, including TopicApiName (which subagent handled it)
AiAgentInteractionStepDmoOne step with start and end timestamps and ErrorMessageText
AiAgentInteractionMessageDmoThe actual input and output text

Session tracing data is stored in Data 360 and consumes credits. A beta Session Trace OTel API exports a single session's trace in OpenTelemetry format for observability platforms such as Splunk, Datadog, or New Relic.

Agent Health Monitoring

Agent Health Monitoring detects silent failures, such as spiking error rates or high latency, and notifies you in near real time.

MetricWhat it tells you
Agent Error RatePercentage of interactions with an error
Average Interaction LatencyAverage milliseconds to respond to an interaction
Escalation RatePercentage of interactions escalated to a human
Agent Response RatePercentage of user turns that got a response within 60 seconds
  • Each alert monitors one metric for one agent and sends an email notification when a threshold is breached.
  • Notifications link directly to the sessions that triggered them, so you can go straight to the trace.
  • Health metrics also appear on the Health tab of Agent Analytics.
  • It's built on Agentforce Session Tracing, visualized with Tableau Next, and available in sandbox and Data Cloud One orgs.

Monitoring Guardrails

Monitor Agent Guardrails gives a focused view of two guardrail metrics:

  • Instruction adherence: how well agents interpret subagent instructions when generating responses
  • Task resolution: how well agents understand the user's intent and resolve the task

This matters where guardrail compliance is a tracked requirement, such as regulated industries, enterprise policy enforcement, and brand safety.

Monitoring Usage and Cost

Agents, data libraries, session tracing, and Testing Center all consume credits. Digital Wallet is the source of truth for consumption. Sandbox agent usage is written to the production org's usage data, tagged with the sandbox org ID and environment type.

Loading diagram...
Observability toolchain in sequence

Scenario Practice

ScenarioTool or control
Agent Analytics dashboards show no data after go-liveConfirm Agentforce Session Tracing (and Audit and Feedback) is enabled
Operations wants an email when a Service agent's error rate spikesAgent Health Monitoring alert on Agent Error Rate
A compliance team tracks whether agents follow instructions over timeMonitor Agent Guardrails (instruction adherence)
A supervisor wants to watch live voice calls handled by agentsOmni Supervisor, Agentforce tab
A contractor should adjust one agent's instructions but not manage other agentsManage AI Agents is org-wide, so restrict who gets it and use process controls
A bad release needs rollbackActivate the previous committed version

Exam Traps

  • Session tracing comes first. Without it, analytics and optimization have no data.
  • Manage AI Agents isn't scoped to one agent.
  • Health Monitoring is for rapid alerts, while Agent Analytics is for trends over time.
  • Live voice monitoring happens in Omni Supervisor, not in the Analytics Voice tab.
Test Your Knowledge

An org activates Agent Analytics after launching an agent, but the dashboards show no session data. Which infrastructure feature must be enabled for observability tools to have data?

A
B
C
D
Test Your Knowledge

An operations team wants an email notification when a Service agent's error rate rises above an acceptable level. Which feature should they configure?

A
B
C
D
Test Your Knowledge

Which statement about the Manage AI Agents permission is accurate?

A
B
C
D
Test Your Knowledge

A supervisor needs to watch active voice calls handled by an Agentforce Voice agent with live transcripts. Where do they do this?

A
B
C
D