| Type | Feature title | Description | Platforms |
|---|---|---|---|
| User features | |||
| New or enhanced feature | Workforce Management scheduling dataset in CX Insights | CX Insights users can filter and group analysis by schedule groups, queues, and agent combinations to connect Workforce Management configuration data to adherence outcomes. Planned schedule activity data such as training, meetings, and breaks, is available as a dimension for analysis so users can identify which activity types correlate with adherence gaps. | Web portal |
| New or enhanced feature | Dataset coverage with variables for CX insights | Supervisors can ask natural language questions in CX Insights across variables. Custom variables bring CRM-sourced context such as customer tier, case type, or issue category into answers about queue and engagement performance, so supervisors can understand the reasons behind aggregate metrics. Admins can select which variables are sent to CX Insights, keeping sensitive customer data from reaching the AI surface without explicit approval. | Web portal |
| New or enhanced feature | Scheduled queries for CX Insights | Users can schedule CX Insights queries to run automatically on a daily, weekly, or monthly basis without re-entering queries manually. Scheduled results are delivered to the user's email with a link to open the query for further exploration. Suggested prompt templates (daily summary, morning briefing, weekly prep, agent actions digest) help users get started. All scheduled queries can be viewed, paused, edited, or deleted from a dedicated panel. | Web portal |
| New or enhanced feature | Project-level instructions and memory for CX Insights | CX Insights remembers project-level rules and individual context automatically. Project instructions are shared rules covering default analysis scope, metric definitions, output format, and business preferences that apply consistently across every conversation in a project. Project memory is automatically generated by the system from conversations to retain long-term context, such as a team's shorthand for a queue, a preferred reporting window, or a correction made in a previous session. Both instructions and memory can be created or updated using natural language, without needing to edit raw configuration. | Web portal |