--- schema_version: "1" id: 6c40d4c4f8f6011f3d19c95fa1ccec8f88e1bd16efbd338658b60e5ff00c904f title: Analyze Data with Agent Optimization collection: admin version: current locale: en-us portal_url: https://docs.salesforce.com/admin/current/en-us/ai/264-0-0/generative_ai_optimize_use.md canonical_url: https://help.salesforce.com/s/articleView?id=ai.generative_ai_optimize_use.htm&release=264.0.0&type=5 source_site: help.salesforce.com content_type: documentation content_hash: 75d5b68f39bfff8fadf9c862ad92f77aed965a09bdea37ffb7bb0519570765cc description: Use Agent Optimization to drill into sessions, analyze quality scores, and identify patterns to improve your agent's performance. products: - Agentforce - Cross Cloud release: "264" --- # Analyze Data with Agent Optimization Use Agent Optimization to drill into sessions, analyze quality scores, and identify patterns to improve your agent's performance. ### Required Editions | Required Editions | | --- | | Agent Optimization is available in Salesforce Enterprise, Performance, and Unlimited Editions with Salesforce Foundations or Agentforce 1 Edition. | ![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 Agent Optimization is available in sandbox and DC1 organizations.
Access and view Agentforce OptimizationAssign the Access Agentforce Optimization and Data Cloud User permission sets
Agent Optimization helps you analyze both voice and chat sessions, view raw and processed session data, filter by modality, and track quality scores to improve your agent's performance. ![Important](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-ai-generative_ai-264-0-0-production-enus/f8ef6498-d7b2-44e3-9b34-ffd5a850aae9/images/icon_important.png) Important If Agent Optimization isn't available, ensure that both **Agentforce Session Tracing and Data Model** and **Agent Optimization** are enabled in **Setup** | **Einstein Audit, Analytics, and Monitoring Setup**. For setup instructions, see [Set Up Agent Optimization](https://help.salesforce.com/s/articleView?id=ai.generative_ai_optimize_setup.htm&release=264.0.0&type=5 "To use Agent Optimization, turn it on in Einstein Setup. Analyze agent sessions, identify knowledge gaps, and explore unresolved interactions based on Agentforce Session Tracing data."). In Agentforce Studio, under **Optimization**, open **Sessions & Intents** to review and improve session behavior. ## Work with the Sessions and Intents Page Go to the Sessions & Intents page to filter, analyze, and export session data for both voice and chat interactions. The page provides powerful tools to analyze your agent's interactions and is divided into Processed and Unprocessed Sessions. Key metrics populate the columns including Intent Summary, Response Summary, Intent Tags, Quality Score, actions performed by the agent, and more. ![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 Currently, sessions created in real time via Email are not reflected in the Sessions and Intents table, so their information is not considered. - **Filter sessions by modality:** Use the modality filter to view sessions by type: Voice, Chat, or All Modalities. - **Processed and Unprocessed Sessions:** The page is divided into **two distinct views.** Processed Sessions have passed through the optimization pipeline, where the system extracts and analyzes customer intents for insights and assigns quality scores. Unprocessed Sessions have not yet gone through the pipeline and may include active sessions or recently closed sessions. For more information about intent processing, see [Use Intents in Agent Optimization](https://help.salesforce.com/s/articleView?id=ai.generative_ai_optimize_intent_use.htm&release=264.0.0&type=5 "Work with intents in Agent Optimization to understand user requests, analyze interaction patterns, and improve your agent's performance."). ![Sessions and Intents page showing the Processed Sessions tab](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_optimization_processed_dasboard.png) - **Session Timeframe Range:** View and filter sessions from the last 24 hours. - **Average Agent Response Latency:** Show the average time elapsed from the end of the user's message to the start of the agent's response. This is the headline latency metric on the session-level view. The table column and filter are hidden by default. - **Transcript Export:** Download transcripts for all sessions currently filtered in the table. - **Responded in:** Shown for both Chat and Voice sessions. Measures the time from the end of the user's message to completion of the agent's response. ## Optimize Voice Sessions Drill into voice sessions to listen to recordings and analyze voice-based interactions. Agentforce Observability supports voice agents. You can drill into any voice session and listen to the recording using the integrated audio player directly from the Sessions page. ![Voice session trace showing the conversation transcript and integrated audio player](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-ai-generative_ai-264-0-0-production-enus/f8ef6498-d7b2-44e3-9b34-ffd5a850aae9/generative_ai/images/aget_optimization_voice.png) Click into any session to view its data and play back audio for voice-based interactions. The voice session trace displays the complete conversation transcript alongside the audio playback controls. Voice uses automatic speech recognition (ASR) to convert speech to text as input to the voice agent. Each word receives a confidence score that indicates how certain the transcription engine was of that word. In the session transcript, words below the confidence threshold appear with a dotted underline. Speech recognition can be affected by background noise, poor call or audio quality, fast speech or varied accents, and specialized domain vocabulary. Word-level confidence scores are captured on the ASR step of the `AiAgentInteractionStep` object in the session tracing data model. Confidence isn't the same as transcription accuracy: a high-confidence word can still be transcribed incorrectly, and a low-confidence word can still be correct. The agent can also recover the intended meaning from context. ![Voice session transcript with a dotted underline on a low-confidence word and a tooltip that the transcription of highlighted words can be inaccurate](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_optimization_voice_asr_transcript.png) The transcript viewer highlights words that can be inaccurate so you can inspect the session in context. Each session also receives an **Audio Quality Score** from 0 through 5 that reflects whether an audio or recognition issue likely affected an important response or outcome. ![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 **Audio Quality Score** is available only for Agentforce Voice customers who use Agentforce Contact Center. For more information about related call-quality scoring, see [Monitor Call Quality with Mean Opinion Scores](https://help.salesforce.com/s/articleView?id=service.voice_setup_mos.htm&language=en_US). Session-level metrics show what happened and how a session ended, but they don't always explain why. Use ASR confidence and audio quality score to investigate whether uncertain recognition, degraded audio, or another voice condition contributed to an abandoned session. To apply the same assessment across multiple sessions, create a conversation-level evaluation in Tests. For instructions, see [Create Custom Evaluations](https://help.salesforce.com/s/articleView?id=ai.agent_studio_testing_center_custom_evaluations.htm&release=264.0.0&type=5 "Custom scorers evaluate AI agent sessions against specific criteria that you define, like tone, brand voice, or business outcomes. Use them alongside default scorers to get a complete picture of agent performance."). For a ready-to-use prompt template that classifies voice ASR and audio quality, see [Custom Scorer Prompt Examples](https://help.salesforce.com/s/articleView?id=ai.generative_ai_optimize_scorer_examples.htm&release=264.0.0&type=5 "Use basic and advanced prompt examples to create custom scorers for common evaluation patterns."). ![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 When you write a scorer prompt template, insert `{!$Input:Session}`. This merge field supplies the evaluator with the full transcript and turn-level ASR metadata from the captured session payload. ## Dive into Specific Intents From the Processed Sessions tab, you can drill into specific intents to identify patterns and opportunities in your agent's interactions. The table displays key metrics for each interaction including Intent Summary, Response Summary, Intent Tags, Quality Score, actions performed by the agent, and more. You can also view intents and their performance in the **Session Trace** on the Session Page. The session trace shows a session flow breakdown: each session is broken down into intents, and each intent is associated with the cluster tag assigned by the clustering pipeline. Use intent tags to group and compare similar user requests across sessions, identify high-volume patterns, and prioritize improvements. To understand how tags are generated, see [Intent Analysis and Clustering](https://help.salesforce.com/s/articleView?id=ai.generative_ai_optimize_intent_use.htm&release=264.0.0&type=5 "Agent Optimization uses intent generation and clustering pipelines to analyze session data. The intent pipeline analyzes sessions to identify and generate intents. The clustering pipeline groups intents by shared user objectives and assigns cluster tags to intents that meet semantic and size thresholds."). ![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 The intent scheduler runs every 3 hours. Intent generation typically takes 4–5 hours, while clustering runs daily and new tags are created weekly. For more information, see [Use Intents in Agent Optimization](https://help.salesforce.com/s/articleView?id=ai.generative_ai_optimize_intent_use.htm&release=264.0.0&type=5 "Work with intents in Agent Optimization to understand user requests, analyze interaction patterns, and improve your agent's performance."). ## Debug and Optimize from the Session Page Deep-dive into specific interactions to understand what happened during user conversations and identify areas for improvement. Click on a session to open the Session Page and deep-dive into that specific interaction. The Session Page shows you exactly what happened during a user's conversation with your agent, helping you understand and fix issues. The Session Page shows **Average Agent Response Latency**, the average time elapsed from the end of the user's message to the start of the agent's response. Chat and Voice sessions also show **Responded in**, the time from the end of the user's message to completion of the agent's response. **Session Page Overview** ![Session page showing three layers: the session list, the session detail with intent breakdown, and the trace panel with step-level detail.](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_optimization_session_page.png) Use the **Interaction Summary** for a concise view of the interaction, then open the **Trace** tab to follow what happened in order. Tracing shows a time-ordered record of processing steps and their duration, so you can see where work ran, how long each part took, and where to look when behavior or performance does not match what you expect. When a user initiates a request, the agent analyzes intent and runs the sequence of actions configured to handle it. The trace reflects that work as distinct steps—for example intent handling, subagent routing, filters, retrievals, variable updates, and action execution—so you can compare what appears in the UI with what you defined in Agentforce Builder. Admins can configure subagents with specialized actions, including delegation to other agents in Single Org, Multi-Agent (SOMA) setups. When delegation occurs, expand the trace step where the subagent was invoked to drill into nested steps. **Session Page with Interaction Summary and Trace** ![Session page with Interaction Summary and Trace tab showing ordered processing steps and timing](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_opimization_trace.png) **Unprocessed Session View:** For sessions still active or those that haven't completed the intent pipeline, you see a "Session processing in progress" banner. Switch to the **Trace** tab to view the full **Session Trace**. **Unprocessed Session View** ![Unprocessed session showing chat session trace with Interaction Summary and Trace tabs](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_optimization_chat_Unprocessed.png) **Processed Session View:** Once processing completes, the session trace displays intents with quality score indicators. Click on an intent to view performance metrics, triggered subagents and actions, and quality score reasoning. **Processed Session View** ![Processed session showing chat session trace with intents, quality scores, and detailed intent metrics](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_optimization_chat_processed.png) On the **Sessions & Intents** page, the **Session Outcome** column provides conversation-level visibility into how your agent performed. **Session Outcome** classifies how each session ended by combining escalation status with LLM-evaluated deflection and abandonment scores. ![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 Before Summer '26, **Session Outcome** used event-based signals, and sessions recorded before Session Outcome was introduced in Spring '26 show `NOT_SET`. Starting in Summer '26, **Session Outcome** uses LLM-based scoring for classification. At session close, Agentforce evaluates a Deflection Score and an Abandonment Score, then applies this decision logic. Session Outcome Decision Logic | Session Outcome | Criteria | | --- | --- | | Escalated | Session was transferred to a human agent. | | Abandoned | Not escalated, and (Abandonment Score = TRUE, or Deflection Score < 3). | | Deflected | Not escalated, not abandoned, and Deflection Score >= 4. | | Ambiguous | Not escalated, not abandoned, and Deflection Score = 3. | | NOT\_SET | No session end signal was received. | **Deflection Score** is a 1-5 rating of whether the user's primary goals were achieved by the end of the session (1 = not achieved, 5 = fully achieved). **Abandonment Score** is a TRUE, FALSE, or UNSURE evaluation of whether the user disengaged due to dissatisfaction or an unresolved issue. Both scores include an evaluation reasoner that explains how the outcome was reached. The explanation is visible when you drill into an individual session. Use this reasoner to understand borderline outcomes and decide whether scorer prompt adjustments are needed. To customize how Deflection and Abandonment are evaluated for your business context, see [Scorers and Custom Scorers](https://help.salesforce.com/s/articleView?id=ai.generative_ai_optimize_scorers.htm&release=264.0.0&type=5 "Scorers evaluate agent sessions for quality and business insights. You can score sessions with prompt templates that run automatically, by API, or manually in Agentforce Studio. Use out-of-the-box scorers, edit existing scorers, or create custom scorers with predefined or open-ended outputs."). ![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 Out-of-the-box LLM calls for Deflection and Abandonment scoring aren't billed against Data 360 credits. Historical data from earlier event-based scoring is preserved. To review calculated fields for reporting and dashboarding, 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.").