Supervisor Dashboard

The QA Dashboard provides a centralized view of quality performance across AI Agent and Human Agent conversations. It combines audit metrics, evaluation outcomes, AutoQA coverage, adherence trends, coaching insights, and interaction analytics to help supervisors monitor quality, identify performance gaps, and prioritize coaching opportunities. The dashboard uses shared global filters to analyze conversation data across AI Agent, Human Agent, or combined conversations. The Conversations Handled By filter determines the conversation handler used for analysis and dynamically displays the applicable filters and evaluation data:

When AI Agent is selected, the dashboard displays AI Agent evaluation data based on configured Experience Flows. AI Agent conversations are filtered using Experience Flow instead of Queue and Agent filters.
When Human Agent is selected, the dashboard displays Human Agent evaluation data based on selected Queues and Agents.
When both AI Agent and Human Agent are selected, the dashboard displays combined quality insights while preserving evaluation attribution based on the conversation handler.

All dashboard widgets update automatically based on the applied filter selections. Using the QA Dashboard, supervisors can:

Monitor quality performance and evaluation trends.
Compare AutoQA and manual audit results.
Analyze failed and fatal interactions.
Track audit progress, coaching activity, and pending reviews.
Evaluate AI Agent and Human Agent performance separately or together.
Identify agents requiring coaching.

Key Features

Capability	Description
Real-time Performance Insights	Provides near real-time visibility into audit performance, agent quality trends, coaching activity, and fatal interactions across conversations.
Handled By Analysis	Filter quality metrics by All, AI Agent, or Human Agent. For handoff conversations, evaluations contribute to the respective evaluator metrics (AI Agent or Human Agent).
Cross-queue Analytics	Analyzes agent performance across all accessible queues without assignment restrictions.
Direction-aware Analysis	Compares inbound, outbound, or combined interaction performance using contact direction filters.
Adherence Heatmap	Visualizes adherence trends, fatal interactions, and evaluation performance based on selected filters.
Agent Leaderboard	Identifies top and bottom performers using audits completed, audit scores, evaluation scores, and failure rates to support targeted coaching.
Evaluation Score Trends	Tracks AutoQA and manual audit score trends across daily, weekly, and monthly time views.
Performance Monitoring	Analyzes score distributions and evaluation performance using selected evaluation forms. Widgets automatically update based on active filters.
Flagged Interactions Visibility	Provides access to flagged interactions across the QA Dashboard, Audit Screen, and Conversation Mining for quality monitoring and coaching.
Pending Review Tracking	Monitors evaluations awaiting QA review, agent acknowledgment, or dispute resolution.
Filter-based Analysis	Applies dashboard-wide filters such as Handled By, language, date range, channel, and contact direction, with synchronized widget updates.
Role-based Access	Allows App Owners, App Developers, App Testers, and Supervisors with Cross Queue Data Access to view data across all queues. Other users can access only their assigned queues.

Access Supervisor Dashboard

Navigate to Quality AI > AutoQA > Dashboard.

Enable the required settings in Quality AI General Settings and assign the appropriate permissions to access features such as Agent Scorecard, AutoQA, Evaluation Forms, Adherence Heatmap, Performance Monitor, and Agent Leaderboard.

Configuration Requirements

Enable the required settings in Quality AI > Settings > Quality AI General Settings to access dashboard features and activate the Agent Accept & Dispute workflow.
Assign the required Quality AI permissions to access features such as Agent Scorecard, AutoQA, Evaluation Forms, Adherence Heatmap, Performance Monitor, and Agent Leaderboard.
Enable Cross Queue Data Access for users to view data across all queues.
Configure and publish evaluation forms and scorecards, and enable AutoQA (for automated evaluation scoring) in Quality AI General Settings.

Dashboard Filters

The QA Dashboard provides shared global filters across all widgets, consistent with the Agent Dashboard and Audit views. Use the Filter panel from the dashboard header to refine quality and performance analysis by Date Range, Evaluation Forms, Conversations Handled By, AI Agent Experience Flows, Human Agent Queues, Human Agents, Channels, Languages, and Contact Direction. All selected filters are applied together when Apply is selected, and dashboard widgets update dynamically based on the applied criteria. By default, the dashboard displays data for All Evaluation Forms, All Queues, All Languages, Last 7 Days, All Channels, and Both Directions. Queue options update dynamically based on the selected evaluation forms.

All widgets update dynamically when filters change.

Date Range

Select a date range using the calendar and apply to refresh the dashboard data. To filter by calendar,

Select the Calendar dropdown.
Choose a required date range.
Select Apply.

The Filter panel provides centralized filtering across all dashboard widgets. Supervisors can filter data by evaluation forms, channels, languages, conversation handler, experience flows, queues, and agents. Filter selections remain pending until you select Apply.

Filter	Description	Supported Features	Affected Widgets
Evaluation Forms	Filters dashboard data using one or more evaluation forms. The available Experience Flows and Queues update based on the selected forms.	Search, Multi-select, Show all, Clear	Evaluation Score, Adherence Heatmap, Fail Statistics, Performance Monitor
Channels	Filters interactions by communication channels such as Voice and Chat.	Multi-select	All widgets
Languages	Filters interactions by one or more configured languages.	Multi-select, Show all, Clear	All widgets
Conversations Handled By	Select AI Agent, Human Agent, or both to analyze conversations by handler. Selecting AI Agent displays the Experience Flow filter, while selecting Human Agent displays the Queues and Agents filters.	Checkbox selection	All widgets
AI Agent → Experience Flow	Filters AI Agent conversations using selected Experience Flows. This filter appears when AI Agent is selected under Conversations Handled By. AI Agent conversations are filtered using Experience Flow instead of Queue and Agent filters.	Search, Multi-select, Show all, Clear	Evaluation Score, Adherence Heatmap, Fail Statistics (Evaluation Form), Performance Monitor (Evaluation Form)
Human Agent → Queues	Filters Human Agent conversations using selected queues. The available Agents update based on the selected queues.	Search, Multi-select, Show all, Clear	Evaluation Score, Adherence Heatmap, Fail Statistics, Performance Monitor, Agent Leaderboard
Human Agent → Agents	Filters Human Agent conversations using selected agents within the selected queues. This filter appears when Human Agent is selected under Conversations Handled By.	Search, Multi-select, Show all, Clear	Agent Leaderboard, Coaching-related widgets

Available filter options update dynamically based on selected values. Evaluation Forms update available Experience Flows and Queues. The Conversations Handled By selection determines whether AI Agent (Experience Flow) or Human Agent (Queues and Agents) filters are displayed.

Filter Behavior

The dashboard applies all selected filters together when Apply is selected.

Select AI Agent, Human Agent, or both under Conversations Handled By.
Select AI Agent to display the Experience Flow filter section.
Select Human Agent to display the Queues and Agents filter sections.
Select both AI Agent and Human Agent to display all applicable filter sections.
Select Apply to apply all selected filters and refresh the dashboard widgets.

When both AI Agent and Human Agent are selected, widgets display combined results while maintaining separate evaluation attribution based on the conversation handler.

For handoff conversations, the dashboard attributes evaluations based on the evaluator type. AI Agent evaluations contribute to AI Agent quality metrics, while Human Agent evaluations contribute to Human Agent quality metrics.

Dashboard Widgets

Provides a high-level summary of audit activity, coaching workload, quality performance, and evaluation review status.

Metric	Description
Total Audits	Displays the total number of completed manual audits.
Avg. Audits per Agent	Displays the average number of audits completed by each agent in assigned queues.
My Pending Reviews	Displays the number of disputed evaluations assigned to the signed-in QA that are awaiting re-evaluation response. The count updates automatically when agents submit disputes and QAs resolve them.
Supervisor Pending Reviews	Displays the number of evaluations awaiting supervisor review or dispute resolution.
Agent Pending Reviews	Displays the number of evaluations awaiting agent acknowledgement or dispute response.
Coaching Sessions Assigned	Displays the total number of coaching sessions assigned to agents.
Agents in Coaching	Displays the number of agents with active coaching assignments in queues the supervisor can access.
Fatal Interactions	Displays the number of interactions that failed due to fatal evaluation rules. If an interaction meets any fatal criterion, the system assigns a score of zero to the entire scorecard.

Agent Performance Metrics display combined metrics when both AI Agent and Human Agent conversations are selected. Metrics related to agents, coaching, and scorecards apply only to Human Agent evaluations.

Audit Progress

Displays the overall audit status of assigned interactions in a donut chart, showing distribution across audit stages. The total in the center represents all assigned interactions, while each segment indicates its current status.

Status	Description
Completed	Number of assigned interactions audited.
Pending	Number of assigned interactions not audited.
In Review	Number of assigned interactions under review.

This metric is visible only when these settings are enabled in Quality AI > Settings > Quality AI General Settings and Agent Accept & Dispute are configured for one or more evaluation forms.

Audit Action

Select Audit to navigate to Conversation Mining > Audit Allocations, where you can start or continue evaluating assigned interactions. For more information exploring and filtering interaction-level data, see Audit Allocations.

Evaluation Score

Displays the trend of the average Kore Evaluation Score (AutoQA) and average Audit Score (manual) over daily, weekly, or monthly interval views based on selected filter options such as Forms, Channels, Languages, Queues, and Agents.

When Agent Accept & Dispute is enabled in Quality AI > Settings, Audit Score reflects the latest revised score after re-evaluation.

Adherence Heatmap

Displays a 7-day adherence snapshot for the selected evaluation form and conversation handler. For AI Agent analysis, adherence data is based on Experience Flow evaluations. For Human Agent analysis, adherence data is based on queue and agent evaluations. Hover over a tile to view adherence percentage, interaction count, and total evaluated interactions for a selected date and agents. Use Mark as Default to set a default evaluation form and maintain consistent data across the Adherence Heatmap and QA Dashboard.

Option	Description
Evaluation Form	Select evaluation form for adherence metrics and fatal interactions.
Language	Filters adherence metrics by selected language.
Experience Flow / Queue	Displays Experience Flows for AI Agent analysis and Queues for Human Agent analysis based on selected handler.
Tooltip Insights	Displays adherence percentage, interaction count, and total evaluated interactions.

Enable AutoQA in Quality AI > Settings > Quality AI General Settings to configure evaluation forms and generate automated scores.

View More Details

Select View More Details to open the detailed Adherence Heatmap and view evaluation form-based trends.

Fail Statistics

The Fail Statistics widget helps supervisors identify quality issues by tracking failed and fatal interactions over time. It provides trend analysis across Evaluation Forms and Agent Scorecards, enabling supervisors to monitor failure rates and analyze performance based on the selected conversation handler. The widget updates dynamically based on dashboard filters, including Conversations Handled By, Evaluation Form, Queues, Experience Flows, Language, Channel, Contact Direction, and Date Range. Use Fail Statistics to:

Monitor the total number of failed interactions.
Compare failed and fatal interaction trends.
Analyze failures by Evaluation Form or Agent Scorecard.
Filter results by Human Agent Queues or AI Agent Experience Flows.
View failure trends across Daily, Weekly, or Monthly intervals.

Fail Statistics displays evaluation data based on the selected Conversations Handled By option. When AI Agent is selected, it shows AI Agent evaluation data based on selected Experience Flows. When a Human Agent is selected, it shows Human Agent evaluation data based on selected Queues and supports Agent Scorecard analysis, which is available only for Human Agent evaluations.

Evaluation Form

Displays failed and fatal interaction trends across selected evaluation forms and queues. Hover over the chart to view detailed failure percentages and metric-level scores.

Agent Scorecard

Displays failed interaction trends based on selected scorecard metrics. If you mark a metric as fatal, assign a zero score to the interaction and flag it across modules. Hover over the chart to view failure percentages and metric-level scores.

The widget updates automatically based on the applied dashboard filters.

Element	Description
Evaluation Form	Selects the evaluation form used to calculate failure statistics.
Queues & Experience Flows	Filters results by Queues or AI Experience Flows. Supports separate tabs with search and multi-select options.
No. of Fails	Displays the total number of failed interactions and the percentage change compared to the previous period.
Failed Interactions	Shows trends of failed interactions over time.
Fatal Interactions	Displays interactions that triggered one or more configured fatal metrics.
Trend Interval	Allows selection of trend view by Daily, Weekly, or Monthly intervals.

The widget updates automatically based on the selected dashboard filters.
When Handled By is set to AI Agent, only AI Agent evaluation data is displayed.
The Agent Scorecard view is unavailable for AI Agent analysis because scorecards apply only to Human Agent evaluations.

Performance Monitor

Displays performance trends and score distributions using Evaluation Forms for AI Agent and Human Agent conversations. Agent Scorecard analysis is available only for Human Agent evaluations.

Evaluation Form

Displays performance trends and evaluation scores for selected evaluation forms and queues. Supervisors can switch between Trends and Distribution views and analyze data across daily, weekly, and monthly intervals.

The score gauge shows the average evaluation score for the selected filters and date range.

View	Description
Trends	Displays evaluation score trends over time using a performance graph.
Distribution	Displays agent score distribution across defined ranges (for example, 0–10, 11–20) over 7, 30, or 90 days.

Performance Monitor - Evaluation Form Distribution

Agent Scorecard

Displays scorecard-based performance trends and score distribution using selected scorecard metrics.

View	Description
Trends	Displays failed interaction percentage trends over time.
Distribution	Displays agent distribution across configured score bands (for example, 0–10, 11–20).

Performance Monitor - Agent Scorecard Distribution

The Agent Scorecard tab displays only when enabled in Quality AI > Settings > Quality AI General Settings.

Agent Leaderboard

Provides a centralized view of ranked agent performance to help supervisors identify top and bottom performers for recognition and targeted coaching. The leaderboard updates dynamically based on the selected Queue filter and works independently of Language and Channel filters. The Agent Leaderboard supports Human Agent performance analysis only. AI Agent conversations are analyzed through Evaluation Form-based widgets such as Evaluation Score, Fail Statistics, and Performance Monitor. Select an agent or View Leaderboard to open detailed performance insights.

Leaderboard Columns

Column	Description
Agents	Displays the agent group name and assigned queue.
Audit Completed	Displays the total number of audited interactions completed by each agent.
Audit Score	Displays the average manual audit score, including the latest revised score for any re-evaluated interactions.
Kore Evaluation Score	Displays the average AutoQA score for audited interactions.
Fail Percentage	Displays the percentage of failed interactions across all audits.

When Agent Accept & Dispute is enabled in Quality AI > Settings > Quality AI General Settings, Audit Score reflects the latest revised score after re-evaluation.

For more information about ranked agent performance and associated conversations, see Agent Leaderboard.

View Leaderboard

Displays top and bottom performers along with their associated conversations.

You can access the full Agent Leaderboard by navigating to:

Quality AI > Dashboard > Agent Leaderboard.
Quality AI > Agent Leaderboard.
Select any agent to view their individual dashboard (Agent Leaderboard or Agent-Specific Dashboard).

Supervisor Insights and Coaching Support

Supervisors can review interactions, evaluation details, bookmarked conversations, and coaching insights to support targeted coaching activities. Supervisors can use bookmarked interactions to assign coaching tasks. The system displays the most recent interactions first. If an agent doesn’t have an assigned scorecard, supervisors can’t view that agent’s scorecard details. Coaching assignments and coaching-related widgets apply only to Human Agent evaluations. For more information, see Supervisor View with Agent-Specific Dashboard and Agent Dashboard - Agent View.

Get Started

Build

Test and Evaluate

Deploy

Analytics and Insights

References

Key Features