---
schema_version: "1"
id: 36f989384f7307ed59462e41ae6b152a75cef9c817a9260e25b8c84880b1d3ac
title: Get Insights with Agent Analytics
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/ai/264-0-0/generative_ai_agent_analytics_use.md
canonical_url: https://help.salesforce.com/s/articleView?id=ai.generative_ai_agent_analytics_use.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: 28edb0557aaecaad9a2494c944d0e85c10008a921f6c40097dcce654c08cacf3
description: Monitor agent performance in Agentforce Studio with Agent Analytics dashboards, then open Sessions & Intents to audit transcripts, compare intents, and address low-quality sessions.
products:
  - Agentforce
  - Cross Cloud
release: "264"
---
# Get Insights with Agent Analytics

Monitor agent performance in Agentforce Studio with Agent Analytics dashboards, then open Sessions & Intents to audit transcripts, compare intents, and address low-quality sessions.

### Required Editions

| Required Editions |
| --- |
| Agent Analytics is available in Salesforce Enterprise, Performance, and Unlimited Editions with Salesforce Foundations or Agentforce 1 Edition. Agent Analytics is available in sandbox, DC1, and Government Cloud organizations. |

![Note](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-ai-generative_ai-264-0-0-production-enus/f8ef6498-d7b2-44e3-9b34-ffd5a850aae9/images/icon_note.png)

Note

**Sandbox usage tracking:** Agent Analytics dashboards show only data that lives in the current org. If you run agents in a sandbox, usage records are not stored in the sandbox itself—they are written to the TenantEnrichedUsageEvent (TEUE) DLO in your home (production) org and tagged with `UsageReportingOrgId` (the sandbox org ID) and `UsageBusinessEnvType` (Sandbox or Production). The Digital Wallet dashboard in the production org is the source of truth for all consumption. To isolate sandbox-only usage, filter the TEUE DLO by `UsageBusinessEnvType = 'Sandbox'`, and optionally by `UsageReportingOrgId` for a specific sandbox.

## Navigate Agent Analytics in Agentforce Studio

To open Agent Analytics, in Agentforce Studio select **Analytics**. Under **Observe & Optimize**, select **Agent Analytics**, then pick your installed Service Agent Analytics or Employee Agent Analytics app. From the agent menu at the top, select a specific agent or **All** to refresh the metrics and charts.

To review individual conversations against your dashboard findings, select **Sessions & Intents** in the same section. On the session table, compare intent summaries, tags, and actions to what the customer needed.

For detailed steps on filters, columns, and exports, see [Work with the Sessions and Intents Page](https://help.salesforce.com/s/articleView?id=ai.generative_ai_optimize_use.htm&release=264.0.0&type=5 "Go to the Sessions & Intents page to filter, analyze, and export session data for both voice and chat interactions.").

## Service Agent Analytics Dashboards

To scope Service Agent Analytics, set the filters at the top for agent, timeframe, channel, and modality as needed. To switch between summary KPIs and segment breakdowns, select the **Overview** tab or the **Performance Insights** tab.

**Overview**

Select the **Overview** tab to review headline KPIs and trends for the agents and channels in your current filter. Compare period-over-period change on the cards, then read the trend and outcome charts to spot regressions or spikes across agents. When you find an area to investigate, open **Performance Insights** or **Sessions & Intents** for the next level of detail.

Select **Metrics Card** or **Table View** to switch between tile layout and a compact table. Select a dimension tab—**Effectiveness**, **Usage**, **Quality**, **Health**, **Trust**, or **Voice**—to load the KPI set and charts for that lens (rates, volume, quality, errors, Trust Layer evaluations, voice-specific measures, and so on).

**Overview**

![Overview tab with effectiveness metrics, trend lines by agent, task resolution stacked bars, and session outcome stacked bars.](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-ai-generative_ai-264-0-0-production-enus/f8ef6498-d7b2-44e3-9b34-ffd5a850aae9/generative_ai/images/agent_analytics_revised_dashboard.png)

Select **Effectiveness** in the overview dimension row to review rate KPIs (deflection, escalation, abandonment, engagement, success) with period-over-period change on the cards. Read the multi-agent trend line for movement over time. Review the **Session outcome** stack for how sessions ended (deflected, escalated, abandoned, ambiguous).

Representative effectiveness and session metrics (Overview)  
| Metric | Description |
| --- | --- |
| Deflection rate | Share of sessions that ended without escalation. |
| Escalation rate | Share of sessions that were escalated to a human or another agent. |
| Abandonment rate | Share of sessions abandoned (for example, timeout or drop-off) relative to all sessions. |
| Engagement rate | Share of sessions with a substantive reply tied to agent-triggered work (see note). |
| Success rate | Share of interactions that completed agent action steps without errors. |
| Total sessions | Count of all sessions, engaged and unengaged. |
| Engaged sessions | Sessions where the customer interacted with the Service Agent in an engaged manner. |
| Deflected sessions | Sessions successfully deflected without escalation. |
| Escalated sessions | Sessions escalated to a higher tier of support. |
| Abandoned sessions | Sessions that timed out or ended without engagement; default session timeout is two hours. |

![Note](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-ai-generative_ai-264-0-0-production-enus/f8ef6498-d7b2-44e3-9b34-ffd5a850aae9/images/icon_note.png)

Note A session is considered engaged only when at least one action has been triggered.

To track response quality over time, select **Quality** in the overview dimension row and review **Quality scores** from the external evaluator (scale 1–5). Compare agents directly from the charts.

**Performance Insights**

Select the **Performance Insights** tab. In **Breakdowns**, select **Subagents**, **Intents**, or **Actions**, choose a segment (or **All**), select a value in **Select Metric**, then compare the data across segments.

**Performance Insights breakdowns**

![Performance Insights tab showing Breakdowns with Subagents selected, session counts by subagent, and average quality score bars with high, medium, and low bands.](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-ai-generative_ai-264-0-0-production-enus/f8ef6498-d7b2-44e3-9b34-ffd5a850aae9/generative_ai/images/agent_analytics_revised_insights.png)

To look up measure names, formulas, and Trust Layer or voice fields for reporting, see [Agentforce Observability Data Model](https://help.salesforce.com/s/articleView?id=ai.generative_ai_agentforce_observability_data_model.htm&release=264.0.0&type=5 "The Agentforce Observability data model combines Agent Analytics and Agent Optimization data with Agentforce Session Tracing. It includes session trace logs, intents, LLM calls, feedback, and Trust Layer metrics for analyzing agent performance.").

## Employee Agent Analytics Dashboard

To monitor internal agents, open Employee Agent Analytics from **Agent Analytics** as you do for Service Agent. Select the **Overview** tab for headline KPIs and trends, or select **Performance Insights** for the same Breakdowns workflow as Service Agent. Set the filters at the top (for example, agent, timeframe, and channel) to match the employee population you support.

**Employee Agent Overview**

![Employee Agent Analytics Overview tab with User Satisfaction selected, showing aggregated positive and negative user feedback counts and a line chart of positive feedback trends for multiple agents over time.](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-ai-generative_ai-264-0-0-production-enus/f8ef6498-d7b2-44e3-9b34-ffd5a850aae9/generative_ai/images/agent_analytics_revised_employee.png)

Select dimensions such as **Effectiveness**, **Usage**, **User Satisfaction**, **Quality**, **Health**, and **Trust** to load the KPIs for that lens. When you select **User Satisfaction**, open **Aggregated Satisfaction Metrics**, then select **Positive User Feedback** or **Negative User Feedback** to compare cards and the multi-agent trend. To look up measure definitions, see [Agentforce Observability Data Model](https://help.salesforce.com/s/articleView?id=ai.generative_ai_agentforce_observability_data_model.htm&release=264.0.0&type=5 "The Agentforce Observability data model combines Agent Analytics and Agent Optimization data with Agentforce Session Tracing. It includes session trace logs, intents, LLM calls, feedback, and Trust Layer metrics for analyzing agent performance.").