Utterance Analysis

Utterance Analysis lets you quickly see how Agentforce (Default) users are using agents, what they’re requesting, and whether the agent was able to handle these requests. These customizable reports can help you refine your subagents and actions so that your agents respond more effectively and accurately.

Required Editions

Available in: Lightning Experience

Available in: Enterprise, Performance, Unlimited, and Developer Editions. Required add-on licenses vary by agent type.

Note Agentforce Analytics is scheduled for retirement starting May 2026. We recommend using Agent Analytics instead.

Important Starting June 17, 2025, Agentforce (Default) will not include new features or improvements and isn’t available in new Salesforce environments. We recommend migrating to Agentforce Employee agent for continued enhancements and support. If you plan to transition to Agentforce Employee agent or make related license changes, complete the migration of your existing Agentforce (Default) agents in advance to avoid potential disruption in agent availability. If you can't complete the migration in advance, you can create new agents after the transition, which can involve some downtime. See Migrate from Agentforce (Default) to Agentforce Employee Agent.

Note Before you begin, enable Feedback in the Einstein Feedback and Monitoring Setup section of Setup.

Utterance Analysis is in the Agentforce (Default) folder in the Dashboard tab. The dashboard includes reports that track users, as well as the input and the agent response type. Reports are run on weekends and the dashboard is updated weekly.

Utterance Analysis dashboard displaying a glossary and reports for unique users, total requests, subagent relevance, top 10 request clusters, and user input analysis.

Utterance Analysis brings similar utterances together into Clusters. Those clusters are in turn grouped into Categories. By grouping information, you can see the overall trends of what users are asking for.

You can also do a reverse search and filter for unsupported requests, marked as system subagents, and see when an agent wasn’t able to create a meaningful response. This information helps to determine when to create subagents and actions that meet what users are requesting.

Utterance Analysis is built on Data 360 reports, which gives you the flexibility to customize it to suit your needs. But be sure to clone the report and modify the clone, not the original, to avoid breaking the analytics processes.