AI-Assisted Manual Audit

AI-Assisted Manual Audit provides a unified workspace for supervisors and QA teams to evaluate voice and chat interactions using AI-generated insights and manual scoring. Evaluators can review conversation transcripts, recordings, metadata, timeline navigation, AI-generated summaries, topics, sentiment, resolution status, evaluation metrics, scorecards, audit history, coaching activities, and AI recommendations. They can confirm or override AI-generated scores, add comments, save partially completed audits, submit evaluations, and edit completed audits when authorized. The workspace supports manual audits for Human Agent, AI Agent (Automation AI), and AI-to-Human handoff conversations using existing evaluation workflows. For AI-to-Human handoff conversations, the workspace evaluates the AI Agent and Human Agent portions using their respective evaluation forms. When you enable Agent Accept & Dispute, agents can review evaluation results, acknowledge scores, and dispute individual metrics. Supervisors review disputed metrics and complete the re-evaluation workflow. For more information, see Understanding Views and Permissions. When you enable Scheduled Processing for supported conversation sources (Agent AI, Contact Center AI (CCAI), and Automation AI), you can manually review completed conversations before Quality AI finishes processing them. Until processing completes, only conversation metadata is available. After processing finishes, Quality AI displays AI-generated insights, transcript analysis, evaluation metrics, and scores.

With Scheduled Processing enabled, supervisors can also open Pending and Validation Failed conversations directly from Conversation Mining before Quality AI processing completes.

Key Capabilities:

Capability	Description
AI Summary and Insights	Displays AI-generated summaries, topics, sentiment, resolution status, and interaction metrics.
Transcript and Recording Navigation	Navigate to relevant transcript messages or recording positions using timeline markers, keyword highlights, evaluation metrics, hold and transfer events, and transcript events to review conversation context faster.
Topics and Intents	Identifies customer purpose and discussion themes.
Sentiment and Emotions	Tracks customer and agent sentiment and emotion trends throughout the interaction.
AutoQA Evaluation	Uses AI to evaluate configured metrics and generate AutoQA scores.
Direction-Aware Evaluation	Applies evaluation forms based on inbound or outbound interaction direction.
Manual Evaluation	Enables evaluators to review and override AI-generated results using Yes, No, or N/A scoring.
Save Draft	Saves draft audits so evaluators can resume them later without losing responses.
Completed Audit Editing	Enables evaluators to edit completed manual audits when the evaluation form enables audit editing and the user account has edit permission.
Agent Acknowledgment and Dispute	Enables agents to review metric-level scores, acknowledge results, or dispute scores with supporting comments. Supervisors can review disputes and provide a written response for each metric.
Audit Logs	Tracks audit activity, AI execution details, and evaluation history.
Audit Trail	Records audit actions, edits, disputes, and review history.
Mark for Coaching	Enables QA users to flag agents for coaching directly from the Audit screen and manage coaching groups without leaving the review workflow.
Multi-language Support	Supports auditing interactions in configured languages.
Direction and Duration Handling	Flags contacts below a configured duration threshold, excludes them from AutoQA scoring, and supports manual audits for those interactions.
Hold and Transfer Evaluation	Evaluates hold etiquette, transfer handling, silence, and cross-talk behavior.
Conversation Support	Supports manual audits for Human Agent, AI Agent (Automation AI), and AI-to-Human handoff conversations across configured languages using existing evaluation workflows.
Comments and Feedback	Supports message-level and metric-level comments with transcript navigation.

Prerequisites

Before using AI-Assisted Manual Audit, confirm the following:

Requirement	Description
AutoQA Permission	Permission to manage metric types in Quality AI > General Settings.
QA Access	Permission to self-assign and perform audits.
Role-Based Access	Appropriate permissions assigned based on your organizational role.
GenAI Settings	Enable sentiment, emotion, and topic modeling features as needed.
Metric Settings	Enable Speech, Playbook, Hold Etiquette, and other required metrics.
Agent Accept & Dispute	Enable Agent Accept & Dispute in Quality AI > Settings > Quality AI General Settings to activate the metric-level acknowledgment and dispute workflow.

Access AI-Assisted Manual Audit

Navigate to Quality AI > Conversation Mining > Interactions > AI-Assisted Manual Audit.

You can open interactions from:

Source	Description
Conversation Mining	Access all conversations in your assigned queues.
Human Agent or Automation AI Conversation Record	Open the Audit page from a Human Agent or Automation AI conversation record. For AI-to-Human handoff conversations, selecting a segment opens the corresponding AI Agent or Human Agent audit.
Allocations > My Evaluations	Open assigned and completed evaluations, including their current review and dispute status.
Allocations > Disputes	Open disputed evaluations assigned to you for re-evaluation.
Review > Pending Review, Disputes, or Resolved (Agent view)	Open completed evaluations to acknowledge scores for evaluations that are awaiting your response or have active disputes.

Audit Workflow

The manual audit workflow varies based on the evaluation form configuration and enabled review features.

Select an interaction.
Review transcript, timeline, and AI insights.
Select Assign to Me if the interaction isn’t assigned.
Complete all required metrics.
Add comments if needed.
Select Mark for Coaching to flag the agent for coaching review.
Select Submit to complete the audit, or select Save Draft to save your progress and finish later. If the evaluation form has disputes configured, the completed evaluation surfaces to the agent for acknowledgement or dispute.

Save an Audit Draft

Save an In-progress audit and resume it later without losing responses. Use this option to complete large audits across multiple sessions, avoid redoing work, and preserve metric responses. The Save option appears after you select or change at least one response. Once all required metrics are complete, this option changes to a dropdown with Save and Submit options.

Audit State	What You See
Zero responses selected or changed	The system doesn’t display the Save option.
At least one response selected or changed, form incomplete	The system displays the Save option.
All required responses complete	The system displays a dropdown with Save and Submit options.

Saving a draft doesn’t send notifications, create an Audit Trail entry, or change the interaction’s position in list or dashboard ordering. The audit remains in its current status until you submit it.

Before You Begin

Assign the interaction to yourself.

Save a Draft

Complete one or more evaluation metrics.
Select Save Draft.
Close the audit or continue reviewing.

The system saves completed responses and comments. The audit remains assigned to you until you submit it.

You can save only in-progress audits as drafts.

Resume a Draft Audit

When you reopen a saved audit, the system restores every previously entered responses and comments, so you can pick up exactly where you left off. Open the draft audit from Assigned to Me. Continue the evaluation and submit the audit when you finish.

Submit an Audit

After completing the evaluation, submit the audit to finalize the results.

Before You Begin

Check you have the interaction assigned to you.
Complete all required evaluation metrics.
Resolve any required validation errors.

Procedure

Review the completed evaluation.
Select Submit.
Confirm the submission, if prompted.

The system records the audit responses and updates the audit status.

After Submission

You finalize the audit. The interaction moves to the next workflow stage when you enable Agent Accept & Dispute. Otherwise, the system completes the audit. The Submit option remains unavailable until you complete all required metrics.

Edit a Completed Audit

Authorized users can update completed manual audits after submission.

Before You Begin

Verify that:

The evaluation form enables Completed Audit Editing.
Your user account has permission to edit completed audits.
The audit is in one of these review states: Completed, Resolved, and Pending Supervisor Review.

Editing isn’t available for: In Progress audits and Pending Agent Review.

Edit a Completed Audit

Open the completed audit.
Select Re-Audit.
Update one or more metric responses or comments.
Select Submit.

The system updates the audit, records all changes in the Audit Trail, and reopens edited metrics for review when applicable.

Edit availability is a form-level setting. By default, existing evaluation forms turn this off. see Understanding Views and Permissions for the permission that controls who can edit.

Edit Availability

You can edit a completed manual audit only when all the following conditions apply:

The evaluation form enables Completed Audit Editing.
Your user account has permission to edit completed audits.
The audit has a supported status: Audited, Pending Supervisor Review, or Resolved.

Audit Status	Edit Available	Description
Draft	No	You can’t edit the audit because it isn’t ready for editing. Continue completing the audit.
In Progress or Assigned	No	You must complete the audit before you can edit it.
Submitted or Audited	Yes	You can edit the audit when the evaluation form enables Completed Audit Editing and your user account has edit permission.
Pending Agent Review	No	You must wait until the agent review is complete before editing the audit.
Pending Supervisor Review	Yes	The system returns edited metrics to supervisor review.
Resolved	Yes	The system returns edited metrics to the review workflow when applicable.

You edit audits at the conversation level. When you enter edit mode, you can edit all metric responses for the conversation, not just a single metric.

If the evaluation form disables Completed Audit Editing or your user account doesn’t have edit permission, you can’t access the Re-Audit option.

What Happens After You Edit

If the evaluation form doesn’t turn on the dispute workflow, your edit simply updates the audit record. If the form turns on the dispute workflow, and you edit a metric the agent acknowledged or disputed, the system reopens that specific metric for review:

The agent receives the updated metric and can provide a new acknowledgment or dispute response.
The supervisor reviews it again through the normal dispute flow.
Metrics you didn’t touch keep their existing acknowledged or resolved state — editing one metric doesn’t reopen the whole evaluation.

Every edit creates a new Audit Trail entry recording the edited metric, the previous response, the updated response, who made the change, and when. See Audit Trail Tab.

Agent Acknowledgment and Dispute

Agents can acknowledge completed evaluations or dispute individual metrics when you enable Agent Accept & Dispute. If an authorized auditor edits an acknowledged or disputed metric:

Only the edited metrics return to the appropriate review stage.
All remaining metrics retain their current review status.
The evaluation returns to a resolved state after the updated review is complete.

Handoff Conversations

A handoff conversation contains multiple conversation segments. For example, an AI Agent may handle the customer first, then transfer the conversation to one or more Human Agents. Each segment is audited independently using its own evaluation form, metrics, score, and review workflow.

Segment Allocation

The system assigns each conversation segment to the participant who handled it.

Conversation Segment	Evaluation Form Used
AI Agent	The system uses the evaluation form assigned to the corresponding Experience Flow configuration.
Human Agent	The system uses the evaluation form assigned to the receiving queue.

The system treats each segment as an independent auditable unit and assigns its own allocation.

Assigning a Handoff Conversation

Before an auditor claims a handoff conversation, the header displays Audit Status: Not Assigned and an Assign to Me menu.

Assignment Option	Segments Assigned
Both	The system assigns both the AI Agent and Human Agent segments for audit by the same auditor.
AI Agent	The system assigns only the Human Agent segment.
Human Agent	The system assigns only the AI Agent segment.

This allows:

A single auditor to audit the entire conversation.
Different auditors own and audit different segments of the same conversation.
After assignment, the header updates to the applicable Audit Status (for example, Pending Agent Review) and displays Audit Progress as a percentage and completed metric count (for example, 100% *16/16).

Confirm whether Audit Progress reflects all assigned segments when Both is selected or only the currently selected segment before publishing.

Switching Between Conversation Segments

The Audit screen displays the conversation journey as a breadcrumb in the header. Example: AI Agent → Transfer → Agent → Transfer → Agent Each icon represents part of the conversation.

Icon	Represents
AI Agent	The AI Agent segment evaluated using the evaluation form assigned to the Experience Flow.
Human Agent	The Human Agent segment evaluated using the receiving queue’s evaluation form.
Transfer	The handoff point between segments. The system doesn’t evaluate this segment.

Selecting a segment filters the Audit page to that segment only, including: Transcript, Overview, and Metrics. The breadcrumb highlights the selected segment. The Metric Type label indicates the active evaluation form, such as AI Agent or Human Agent.

Per-Segment Overview and Metrics

Selecting a segment filters the right-hand panel to that segment’s data:

Overview displays the segment’s own Kore Evaluation Score (labeled AI Agent Score for AI Agent conversation segments), Points Total, Configured Topics, Generated Topics, Overall Resolution, and Sentiment.
Metrics displays the segment’s own By Question metrics, scored independently using the assigned evaluation form—for example, Did the Automation AI agent welcome the customer?' for the Automation AI conversation segment, and Did the agent greet the customer professionally?` for the Human Agent segment.

Each segment maintains its own metrics, score, and review status. Scoring one segment doesn’t affect any other segment, and each segment progresses through the audit workflow independently.

Audit Screen Headers

The header identifies the conversation, current audit stage, and available workflow actions.

Element	Description
Agent Name	Displays the name of the agent whose conversation is under evaluation.
Date and Time	Displays when the interaction occurred.
Audit Review Label	Displays the current audit stage. See the below Audit Review Status labels.
Review Status Badge	Displays the current workflow state (for example, Assigned, Pending Agent Review, Pending Supervisor Review).
Mark for Coaching	Flags the evaluation for coaching and follow-up.
Cancel	Discards unsaved changes.
Submit	Saves the evaluation or re-evaluation and routes it according to the configured workflow.

Audit Screen Components

The Audit Screen combines conversation playback, AI insights, evaluation metrics, and audit actions in a single workspace.

Component	Description
Transcript	Displays the conversation transcript, recording controls, search, and synchronized playback.
Timeline	Displays conversation events, adherence markers, hold events, transfer events, and playback position.
Metrics Panel	Displays evaluation metrics, AI recommendations, manual responses, comments, and AI Justification.
AI Insights	Displays AI-generated summaries, topics, sentiment, resolution, and conversation insights.
Audit Progress	Displays evaluation completion progress.
Audit Actions	Displays available actions, such as Save Draft, Submit, Re-Audit, Mark for Coaching, and Cancel, based on the audit state.

Use transcript navigation to move directly to the relevant part of a voice conversation while reviewing an audit. You can navigate directly from:

Evaluation metrics by selecting View Chat.
Hold initiation timestamps.
Transfer initiation timestamps.
The system displays individual customer and agent transcript messages when you select Enable message-to-recording navigation.
For transcript messages, hover over a message and select the Play icon to start the recording from the corresponding timestamp.

Message-to-recording navigation is available only for voice conversations and is disabled by default.

Transcript and Recording Navigation helps reviewers move directly to the relevant part of a voice conversation without manually searching the recording. You can navigate directly from supported evaluation metrics, timeline events, and transcript messages. Navigation supports:

Navigation Source	Behavior
View Chat	Opens the related transcript location and synchronizes the recording.
Hold initiation timestamp	Opens the transcript and recording at the hold event.
Transfer initiation timestamp	Opens the transcript and recording at the transfer event.
Transcript message	You can start playback from the selected customer or agent message when Message-to-Recording Navigation is enabled.

The system disables Message-to-Recording Navigation by default, and you can enable it when needed. Enable it to play audio directly from individual transcript messages. When enabled for voice conversations:

Hover over a customer or agent transcript message.
Select Play.
The recording starts from the timestamp associated with that message.

The feature uses transcript message timestamps to synchronize playback with the corresponding recording position.

Applies only to voice conversations and is disabled by default. Enable it to display the Play action for transcript messages with available navigation data. Chat conversations don’t support transcript playback.

Audit Review Tabs

The system displays Audit Review statuses based on the selected Allocations tab and audit workflow stage, helping you track review progress from Assigned through Pending Supervisor Review, Resolved, and Closed.

Label	Description	What It Shows
Unassigned	Shows that no auditor or reviewer has claimed the interaction for review.	Displays interactions that are available for assignment and aren’t assigned to any agent.
Assigned	Shows that the system assigns the audit review to the current auditor or reviewer.	Audit Review → Assigned to Me (audit assigned to you for review).
Pending Agent Review	Shows that the audited agent must review the evaluation, acknowledge it, or respond before the workflow can continue.	Audit Review → My Evaluations (awaiting the agent’s review, acknowledgement, or response).
Pending Supervisor Review	Shows that a supervisor must review and decide on the audit or dispute.	Audit Review → My Evaluations, Audit Review → Disputes (awaiting supervisor review and decision).
Resolved	Shows that the reviewer or supervisor completed the review process and reached a resolution.	Audit Review → My Evaluations (after resolution).
Closed	Shows that the system completed the audit review workflow and no further action is available.	The system finalizes the audit review and prevents further actions.

Processing Status

Processing Status indicates whether Quality AI has completed conversation processing.

Status	Description
Processed	Quality AI completed conversation processing. All audit insights and evaluation data are available.
Pending	The conversation is waiting for processing. Only conversation metadata is available.
Validation Failed	Quality AI couldn’t process the conversation because validation failed. Conversation metadata remains available, but AI-generated analysis and evaluation data are unavailable.

Audit Screen Tabs

The Audit Screen provides role-based access to evaluation, transcript review, audit history, and dispute management.

Tab	Who Sees It	Description
Audit	Supervisor, Agent	Supports transcript review, scoring, AI insights, and dispute responses.
Conversation Details	Supervisor, Agent	Shows interaction metadata, channel, direction, scores, identifiers, and custom fields.
Audit Logs	Supervisor, Agent	Records audit history, user actions, and AI execution logs.
Audit Trail	Supervisor only	Records all evaluation actions from creation to resolution.
Audit Review	Supervisor, Agent	Shows audit stage, workflow status, and dispute handling actions.

Audit Tab

The Audit tab combines transcript review, AI analysis, scoring, dispute handling, and coaching workflows.

Section	Description
Transcript and Timeline (Left)	Displays timestamps, speaker labels, highlights, comments, and synchronized playback for voice interactions.
AI Insights or Metrics Panel (Right)	Shows evaluation metrics, AI-generated scores, adherence status (Yes/No/N/A), manual scoring, and dispute threads for each metric.

Audit Progress

The audit progress bar at the top of the metrics panel tracks evaluation completion across all scoring sources. Its status varies by Allocation tab and audit workflow stage.

Element	Description
Audit Progress Indicator (Percentage + Bar)	Shows overall audit completion as a percentage and progress bar based on completed out of total configured metrics (for example, 0% • 0/24).
Audit Progress Tooltip	Shows a breakdown of completion by evaluation source, such as Question, Speech, Playback, Value, AI Agent, Transfer, Hold, and Manual. Displays values as Completed/Total for each source.
Audit Count	Shows completed evaluations out of total configured evaluations across all scoring sources.

Note: The tooltip displays only configured evaluation sources. The progress indicator updates automatically as users complete metrics. The Submit button remains disabled until all required metrics are completed.

Mark for Coaching

The Audit screen includes a Mark for Coaching action that enables QA users to create coaching recommendations directly from an audit. Only users with the required QA permissions can access this action.

Individual Agent Coaching

Select Individual Agent to create a coaching recommendation for the agent associated with the audited interaction.

Field	Description
Coaching Method	Select the coaching framework or template to use.
Coaching Area	Select one or more coaching areas identified during the audit.

Group of Agents Coaching

Select Group of Agents to create a coaching recommendation for a predefined coaching group.

Field	Description
Coaching Method	Select the coaching framework or template to use.
Group	Select an existing coaching group.
Add New Group	Create a new coaching group if a suitable group doesn’t exist.

Add New Group

Select + Add New Group to create a coaching group.

Field	Description
Group Name	Enter a unique name for the coaching group.
Description	Enter additional information about the group’s purpose or objectives.
Coaching Method	Select the coaching method associated with the group.
Coaching Area	Select the category of coaching metrics to associate with the group (for example, Agent Attribute).
Search Agent Attribute to Add	Search and select agent attributes to include in the group.
Assigned Agent Attributes	Displays selected attributes. Shows No Agent Attribute Added if empty.

Coaching Recommendation Creation

When a QA user saves a coaching recommendation:

The system creates a coaching recommendation based on the selected coaching type.
The system associates the recommendation with the audited interaction and selected coaching areas.
The system assigns the recommendation to the selected coaching group.
The coaching recommendation becomes available for subsequent coaching activities and tracking.

Available coaching methods, groups, and coaching areas depend on the coaching configurations defined in the system.

Supervisor View — Review Panel

The review panel on the right displays evaluation metrics, reviewer responses, comments, and dispute history. Supervisors can review disputed metrics, update responses, and resolve disputes.

Element	Description
Review Progress	Displays the percentage of completed metric evaluations and the number of completed metrics out of the total configured metrics.
Metric Group	Displays metrics grouped by evaluation category, such as By Manual Evaluation.
Metric Count	Displays the number of metrics within the selected evaluation category.
Metric Question	Displays the evaluation question under review.
Response Options	Enables the supervisor to select the evaluation outcome, such as Yes, No, or N/A.
Filter	Filters metrics within the selected evaluation category.
Comments & Dispute	Displays comments, dispute history, and responses associated with the metric.
User Timeline	Displays comments with the contributor name, role, and timestamp.
Accept	Accepts the dispute or updated response and finalizes the decision for the metric.
Deny	Rejects the dispute and retains the existing evaluation outcome.
Status Indicator	Displays the current status of the metric, such as Agent Accepted.

Comments & Dispute

The Comments & Dispute section displays the conversation history associated with a metric.

Element	Description
Reviewer Comment	Displays comments added by a supervisor or QA reviewer.
Agent Comment	Displays comments submitted by the agent during review or dispute.
User Information	Displays the contributor’s name, role, and timestamp.
Status Update	Displays metric-level actions such as Agent Accepted.

Dispute Resolution

When a metric dispute occurs, the system helps supervisors to review the dispute history and take one of the following actions

Action	Description
Accept	Accepts the agent’s dispute, updates the evaluation outcome if required, and resolves the dispute.
Deny	Rejects the agent’s dispute, retains the current evaluation outcome, and resolves the dispute.

The Comments & Dispute section stores the full review history for each metric, including supervisor comments, agent responses, dispute notes, and resolution status in chronological order.

Agent View — Review Panel

The system enables agents to review evaluation results and respond to metric-level evaluations when dispute functionality is active.

Element	Description
Metric Question	Displays the evaluation question.
Outcome Options	Displays the evaluation result selected by the reviewer.
Comments & Dispute	Displays review comments, dispute history, and resolution updates.
Accept	Acknowledges the evaluation result.
Dispute Comment	Enables the agent to provide justification when disputing a metric.
Status Indicator	Displays the current review status, such as Agent Accepted or Disputed, Accepted, or Denied.

Agents can respond at the metric level instead of the full evaluation. When disputes are enabled, the system requires comments for disputed metrics before submission. When disabled, the system shows the review in read-only mode and disables dispute actions.

Audit Evaluation

AI Overview

Displays conversation insights through AI-powered widgets, helping supervisors evaluate key metrics without reading full transcripts. This displays high-level evaluation details and scoring:

Element	Description
Kore Evaluation Score	Displays the Auto QA score for the interaction (before manual evaluation).
Points Total	Shows the achieved score out of the maximum possible score (for example, 4.00 / 100).
Configured Topics	Lists taxonomy-based topics detected in the interaction.
Generated Topics	Displays AI-discovered topics beyond configured taxonomy.
Overall Resolution	Indicates resolution status (for example, Resolved or Not Applicable).
Sentiment	Displays overall interaction sentiment. Shows No Analysis Found if sentiment is unavailable.

Score Summary

Displays key behavioral and linguistic metrics:

Metric	Description
Empathy Score	Measures agent empathy based on conversation analysis.
Sentiment Score	Aggregated sentiment score for the interaction.
Crutch Word Score	Measures usage of filler words (for example, `um`, `uh`).

If analysis is unavailable, these values display as NA.

Topics and Intents

Element	Description
Topics	Identifies key discussion themes using NLP and taxonomy-based classification.
Configured Intents	Intents mapped to predefined taxonomy with click-through navigation.
Generated Intents	AI-detected intents with sentiment indicators.

Resolution and Sentiment

Element	Description
Overall Resolution	Indicates whether the interaction was successfully resolved.
Topic Sentiment	Displays sentiment (positive, neutral, negative) for each topic.

Generated Topics

Expands topic discovery beyond configured taxonomy.
Provides topic-level sentiment insights.
Enhances visibility into conversation patterns.

Transcript and Timeline

The Transcript provides a unified, time-synchronized view of the interaction across chat and voice.

Speaker-separated conversation (Agent and Customer).
Timestamped utterances.
Keyword highlighting and navigation.
Inline and clickable comments.
Audio playback with synchronized transcript (voice only).

Sentiment Analysis

Shows the overall sentiment of the customer and agent across three phases of the call.

Phase	Description
Call Opening	From agent transfer to issue identification.
Development	From issue identification to resolution discussion.
Call Closing	From resolution discussion to call termination.

Sentiment Ratio

Displays the distribution of sentiment across the interaction as a percentage breakdown (Positive, Neutral, Negative). If no data is available, it shows No Sentiment Ratio Found.

Sentiment	Meaning
Positive	Customer satisfaction, successful resolution.
Neutral	Standard interaction without strong emotion.
Negative	Dissatisfaction or unresolved issues.

Sentiment Patterns

Pattern	Meaning
Negative → Positive	Recovery and successful resolution
Positive → Positive	Consistent positive experience
Neutral → Positive	Improved experience
Positive → Negative	Service degradation
Neutral → Negative	Missed expectations
Negative → Negative	Persistent dissatisfaction

Resolution-Aware Scoring: prioritizes final sentiment and produces a weighted interaction score. Scores use a 1-10 scale (5 = Neutral, 7 = Positive) and produce a final classification of Positive, Neutral, or Negative.

Emotion Analysis

Tracks emotional signals for both agent and customer across the timeline.

Agent Emotions: empathy, patience, happiness, frustration, confusion.
Customer Emotions: satisfaction, anger, confusion, churn risk, escalation.

Rank emotions by duration percentage from highest to lowest and display the top three emotions for each participant using timeline-based visualization and emoticon indicators.

Emotion Analysis

Section	Description
Agent Top Emotions	Dominant agent emotions
Customer Top Emotions	Dominant customer emotions

Displays No Emotion Found if unavailable.

Conversation Insights

Metric	Description
Customer Talk Ratio	% of time customer speaks
Agent Talk Ratio	% of time agent speaks
Silence	% of inactive time

Agent Speech Insights

Metric	Description
Speaking Rate	Words per minute
Crutch Words	Filler word count
Empathy Score	Speech-based empathy

Transcript and Timeline

Displays the full interaction with:

Speaker-separated messages
Timestamps
Keyword highlights
Audio playback (voice only)
Clickable navigation markers

By Question (Audit)

The By Question section evaluates interactions using configured audit questions through AI-generated analysis and manual validation.

Evaluation Components

Element	Description
Question Card	Displays the evaluation question.
Evaluation Options	Displays Yes, No, or N/A scoring options.
Auto QA Result	Displays the AI-generated evaluation result.
AI Justification	Displays reasoning and supporting evidence for AI scoring.
View Chat	Navigates to the related transcript section.
Add Comment	Adds metric-level comments.
Audit Progress Bar	Displays audit completion progress.

AI Justification

The AI Justification section uses LLM-generated explanations to clarify Auto QA decisions in By Question metrics. It explains Adhered, Not Adhered, and Not Applicable outcomes and improves transparency by showing why a metric passes, fails, or isn’t evaluated. What AI Justification displays:

Scenario	What the Justification Shows
Adhered - Yes	The system confirms that the agent met the expected behavior and may include supporting context in its reasoning.
Not Adhered (Omission)	The system identifies that the expected behavior isn’t observed across the interaction. The system doesn’t display timestamps because no specific message or event causes the failure.
Not Adhered (Violation Event)	The system identifies a specific message or behavior that causes non-adherence. The system includes timestamps only for violation scenarios where a specific conversation event causes the failure (for example, when an agent displays rude behavior).
Not Applicable (Dynamic By Question)	The system generates an LLM-based justification explaining why the trigger intent wasn’t detected in the conversation. This displays in the Reasoning section and helps users refine trigger prompts during design time.
Outcome	Displays the evaluation result as either adhered or not adhered. The system doesn’t display `Not Applicable` as a standard outcome; instead, AI Justification handles it for Dynamic By Question metrics.
Reasoning	Provides an expandable explanation of the evaluation decision. It explains why the system assigns the outcome, highlights relevant conversation context or missing behavior, and gives evaluation-specific justification instead of a generic summary.

Dynamic By Question – Not Applicable Justification

For Dynamic By Question metrics, when the system doesn’t detect the trigger intent, it generates an LLM-based justification explaining the absence of relevant conversational evidence and why the intent doesn’t qualify for evaluation. This helps users refine and optimize trigger prompts during design time.

Timestamp Generation Rule

Timestamps included: When a specific agent message or event causes a violation (for example, rude or non-compliant behavior).
Timestamps not included: For omission scenarios where expected behavior is missing and no specific message or event caused the outcome.

Timestamp Examples

Valid (Violation-Based): Professionalism metric → Agent used rude language → timestamps displayed for relevant messages.
Invalid (Omission-Based): Greeting metric → Agent doesn’t greet → no timestamps displayed.

Adherence Filter Status

Filter and sort compliance metrics by adherence status:

Status	Description
Adhered	The response meets the compliance requirement.
Not Adhered	The response doesn’t meet the compliance requirement. Display timestamps only for violation scenarios where a specific message or event causes the issue, and don’t display them for omission-based failures.
Not Applicable	For static metrics, the metric isn’t relevant to the interaction context. For Dynamic By Question metrics, the trigger intent isn’t detected, and the system provides an LLM-based justification explaining why.

Enables quick filtering and navigation by keyword or QA question, with auto-scrolling of transcripts and relevance-based matching. Keyword filters applied on the Conversation Mining page carry over to the Audit screen.

Feature	Description
Timeline Integration	Visual markers show exact keyword positions on the timeline. Select a marker to jump to that point in the transcript.
Keyword Highlighting	Highlight matched keywords inline using multiple colors and don’t highlight excluded keywords.
QA Question Mapping	Keyword matches link to relevant QA questions and their scoring impact in the AI Overview panel, including speaker attribution and count.
Context Display	Selecting a keyword expands the surrounding transcript and shows speaker labels, sentiment, and QA impact.
Expand or Collapse View	Expand the Keywords Found panel when keyword filters are active and collapse it when no filters aren’t in use.
Speaker Filtering	Filter keyword hits by agent or customer.
Session Preservation	The system saves keyword filters for the session until you clear them.
Clear Filter Keywords	Removes all include or exclude keyword filters from the transcript while keeping other filters unchanged.

Omissions

Highlights cases where the agent doesn’t follow configured compliance requirements, such as playbook steps or dialog tasks. This includes omitted playbook steps for playbook metrics and omitted dialog tasks for dialog metrics. The system displays only when it has configured relevant metrics for the interaction.

Violations

Highlights speech metric violations that occurred during the call (for example, Cross Talk, Dead Air, or Speaking Rate Violation). Each violation includes a timestamp so you can navigate directly to that point in the recording.

Violations apply to Voice channel interactions only.

By Playbook

Enables evaluators to assess adherence to configured playbook metrics. Displays for each playbook metric:

Configured minimum adherence.
Observed adherence within the interaction.
Missing steps not completed during the interaction.
Expected vs. observed steps in a dropdown format.
To audit Speech and Playbook metrics, enable Audit Speech Metrics and Audit Playbook Metrics under Settings. If not enabled, these metrics show in view-only mode.

Adherence Scoring Logic

Result	Condition
Adhered	Similarity score meets or exceeds the configured threshold (for example, ≥ 60%).
Not Adhered	Similarity score < configured threshold.
N/A	Trigger not detected in the interaction.

By Value

Tracks value-related metrics during interaction evaluations. Leverages GenAI to analyze agent behavior beyond predefined scripts. Agent Adherence fields:

Source System Value - Value obtained from the source system.
Agent Mentioned Value - Value mentioned by the agent during the conversation.
AI Justification - Explanation of the AI’s adherence decision.
GenAI-based adherence - Combines business rule validation with tolerance range analysis.
Custom script adherence - Includes the agent-mentioned value and business rule justification.

By AI Agent

Delivers advanced sentiment analysis through GenAI, enabling Post-Interaction Sentiment Analytics and Key Emotion Moments. Integrates with GenAI Copilot to leverage LLMs for detailed post-interaction insights. Key capabilities:

Real-time AI-driven analysis.
Sentiment and emotion detection.
Topic modeling and intent recognition.
Predictive analytics.

AI Justification fields (for GenAI-based evaluations):

Clear reasoning for the AI’s Yes/No outcome (adhered/not adhered/not applicable) with observation time.
Evidence of trigger presence or absence for dynamic adherence types.
Specific agent behaviors that influenced the metric outcome.
Timestamps for all relevant conversation segments.

Adherence Filter Status Filter and sort compliance questions by adherence status:

Status	Description
Adhered	The response meets the compliance requirement.
Not Adhered	The response doesn’t meet the compliance requirement.
Not Applicable	The question isn’t relevant to this specific context.

Conversation Insights

Provides AI-generated overviews of customer interactions without requiring a full transcript review.

Metric	Description
Customer Talk Ratio	Percentage of total call duration the customer is speaking.
Agent Talk Ratio	Percentage of total call duration the agent is speaking.
Silence Percentage	Call time in which neither party speaks (excludes hold time).
Speaking Rate	Agent speech speed in Words Per Minute (WPM).

Conversation Insights are available for voice interactions only.

Agent Speech Insights

Displays agent-specific performance metrics.

Metric	Description
Speaking Rate	Words Per Minute value.
Crutch Words	Count of filler words (for example, “um,” “uh,” “like”).
Empathy Score	Measurement of empathy in agent utterances.

Comments

Displays feedback submitted by auditors during the evaluation process. Comments appear inline within the Transcript and in the Comments tab. The system displays the Commenter details according to privacy settings (for example, Hide Auditor Details). Supports message-level and metric-level feedback with direct navigation to relevant points in the transcript.

Adding a Message-Level Comment

Select Assign to Me to begin auditing the conversation.
Hover over any message in the Transcript section — a Comment icon displays.
Select the Comment icon and enter a comment Name and Comment text (both required).
Add or delete your comment before sending.
Select Send to publish the comment.

When submitted, the Inline comments box shows:

Inline in the Transcript, linked to the corresponding message.
In the Comments tab with the comment title, text, and commenter details (based on privacy settings).

Auditors and supervisors can add comments in By Question, By Value, and By AI Agent metrics when the audit is self-assigned.

Comment Types

Type	Description
Metric Comments	Added to specific evaluation criteria (By Question, By Value, or By AI Agent). Select + Add Comment, enter your comment, then Select Save.
Message Comments	Contextual comments added at the message level in the Transcript. Support click-through navigation for quick review.

All users — including agents without QA permissions — can select a comment to navigate to the related message. The system centers the commented message in the Transcript window, enabling agents to review feedback from supervisors and QA auditors.

Near-Miss Scenarios

Near-miss evaluations flag responses that resemble but don’t meet adherence standards. Applicable only in Deterministic Adherence mode. How it works:

The system compares agent responses to predefined similarity thresholds.
The system flags near-miss cases for auditor review.
When you Select the View, the system marks the evaluation as Yes (highlighted in green) and highlights the relevant customer response.

By Question metrics are selected by default and can’t be deselected.
Auditors can only audit the metric types they have selected.
Supervisor score calculation includes all enabled metric types.

Self-Assignment for Audit

QA users (auditors or supervisors) can self-assign unclaimed interactions for auditing. The system excludes interactions that it has audited, completed, or assigned to another user. To self-assign an interaction:

Navigate to the Conversation Mining page.
Select an interaction that isn’t audited or assigned.
Select Assign to Me. A success message confirms the assignment.
The system marks the interaction as Self-Assigned on the Audit Allocations page and becomes unavailable for reassignment.

Only users with QA permission can add feedback comments at any point in the conversation, regardless of the evaluation metrics.

Audit Submission

The system displays the Submit option when any interactions assigned to you through Audit Allocations. Before submitting:

If By Question, By Value, or By AI Agent metrics are present, select appropriate responses for all required audit questions.
Ensure the adherence percentage totals 100%.
Select Submit.

After submission:

The system marks the interaction as Self-Assigned on the Audit Allocations page.
The audited interaction is unavailable for reassignment.
You can’t re-audit a completed and submitted interaction.

Agent access to scored interactions setting controlled by the Agent Access to Scored Interactions:

Setting	What agents see
Only manually audited interactions	Supervisor Audit Score interactions with Date & Time and Queues.
Manually audited and Auto QA scored	Kore Evaluation Score (Auto QA) and Supervisor Audited Score interactions.

Hide Auditor Details for Agent:

On - The system anonymize the auditor details in the audit screen.
Off - Auditor details are visible.

Only supervisors can view auditor details. Agents can’t see auditor details.

Search

Provides keyword search across the entire transcript to locate specific topics, compliance issues, customer concerns, or training opportunities.

Conversation Details Tab

Provides contextual and audit-related information for the selected interaction, including direction and custom fields, helping supervisors review the interaction context before or after evaluation. Conversation Details:

Start Time, Termination Time, End Time, Agent Name, Queue, Channel, Contact Direction, Customer Phone, CSAT, Disposition, Evaluation Form, and Language.

Audit Details:

Auditor Name, Audited Date, Audit Score, and Kore Evaluation Score.

Identifiers (each includes a copy icon):

Identifier	Example Value
Call ID	NA
Session ID	`699d3d5ef39661f7c0aa4b95`
Channel User ID	NA
Channel Direction	Inbound or Outbound.
Call Conversation ID	NA
Agent Conversation ID	`c-358c3b1-d472-4c2a-89bd-eebcca3dxxxx`
User ID	`u-e481d17b-aba0-5110-9377-05bc36f0xxxx`

You can also use Assign to Me on this tab to assign the interaction to yourself for audit.

Custom Fields

The Custom Fields section displays business-specific metadata ingested with this conversation from Express File or Agent AI integrations. Each field shows as a header-value pair. If no custom fields are available, the section displays No custom fields found.

Custom fields reflect only the fields ingested with this specific conversation record. Fields vary across conversations based on the source integration and the metadata included at ingestion time.

Right Metadata Panel

The right panel displays the following additional interaction context:

Start Time: Timestamp when the conversation started (for example, 10 April 2026, 7:00:00 AM).
Termination Time: Timestamp when the system terminated the conversation.
End Time: Timestamp when the conversation ended.
Agent: Name of the agent who handled the interaction.
Queue: Queue assigned to the interaction (for example, AWSPublicQueue).
Channel & Direction: Channel type and contact direction (for example, Voice — Inbound).
Customer Phone: Customer’s phone number, if available.
CSAT: Customer satisfaction score, if collected.
Disposition: Disposition applied to the conversation.
Evaluation Form: Name of the evaluation form applied (for example, New Points Based).
Language: Language of the conversation (for example, English).

Audit Logs Tab

This tab provides AI processing details for an interaction. It displays feature execution results, token usage, execution time, and payload information to help users review AI activity and investigate processing issues. Information is organized into process summaries and detailed execution records.

Process Status

This section displays the execution status of AI features used during interaction analysis.

Category	Description
Auto QA	Displays execution results for AI-powered audit evaluations and adherence analysis, such as Dynamic By Question and Adherence.
Conversational Intelligence	Displays execution results for conversation analysis features such as topic detection and sentiment analysis features, such as Churn Detection and Crutch Word Score Determination.

The system groups features into categories and displays aggregated request and response token counts for each category within the processed interaction. Feature Status Fields

Field	Description
Feature Name	Displays the AI capability executed for the interaction.
Failure Reason	Shows the error when execution fails. Otherwise, it displays blank. Common causes include invalid or missing transcript data.
Status	Displays the execution result, such as Success or Failed.

GenAI Execution Records

Displays detailed execution records for individual GenAI features. Where, you can filter records by Gen AI Feature and Status. Each record displays as an expandable card with a summary of the AI execution.

Field	Description
Feature Name	Displays the executed GenAI capability, such as By Value metric extraction for Quality AI or GenAI-based agent answer adherence and customer trigger detection.
Execution Duration	Displays the time taken to complete processing.
Request Tokens	Displays the number of input tokens sent to the model.
Response Tokens	Displays the number of output tokens generated by the model.
Model	Displays the AI model used for execution, such as GPT-4o.
Status	Displays the execution result, such as Success or Failed.

Execution Details

Field	Description
Integration Type	Displays the execution source, such as System.
Language	Displays the language used during processing. Otherwise it shows blank when unavailable.
Prompt Type	Displays the prompt category, such as Default or Custom.
Request Tokens	Displays the number of input tokens used for the execution.
Response Tokens	Displays the number of output tokens generated by the model.
Timestamp	Displays the date and time when the execution occurred.
Response Duration	Displays the processing time for the execution.
Status	Displays the execution result, such as Success or Failed.

View Payload

Select the View Payload eye icon to open detailed execution information for a GenAI feature. The payload window displays execution metadata along with request and response payloads. Execution Metadata This displays the summary information about the selected execution.

Field	Description
Feature Name	Displays the selected GenAI feature.
Model	Displays the AI model used for processing.
Prompt Type	Displays the prompt category, such as Default or Custom.
Duration	Displays the execution time.
Status	Displays the execution result.
Request Payload	Displays the input sent to the AI model, including configuration settings, prompts, and input messages.
Response Payload	Displays the output generated by the AI model, including responses, annotations, and execution results.

Payload Actions The payload viewer provides tools for inspecting payload content.

Action	Description
Format	Formats the payload for easier reading.
Compact	Displays the payload in a condensed view.
Copy	Copies the payload content to the clipboard.
Full Screen	Opens the payload in an expanded view for detailed inspection.
Close	Closes the payload window and returns to the Audit Logs tab.

Payload content varies based on the selected AI feature, model response, and processing results. Execution Status This indicates whether a feature completed successfully or failed. When a failure occurs, the system records the reason when available. Select Assign to Me to assign a log entry to yourself for audit review. The system records who assigned it and when, and displays the assigned user in the header and audit history. Payload Visibility: View Request and Response payloads with options to expand/collapse, format or compact, copy to clipboard, or open in full-screen mode for debugging.

Audit Trail Tab

The Audit Trail tab provides a history of audit activities, including evaluations, disputes, re-evaluations, assignments, and status updates. It also displays audit information such as the audited agent, audit date and time, and review status. This can include one or more allocation records based on the audit history. Each allocation displays assignment summaries and evaluation details. Dispute and re-evaluation records display when applicable.

Allocation Summary

Displays an overview of an audit assignment.

Field	Description
Allocation Assigned By	Name of the user who assigned the audit.
Evaluation Outcome Count	Summary of metric results within the allocation.
Evaluation Score	Overall score calculated from evaluated metrics.

Evaluation Outcome Count The system groups metric results into the following categories.

Outcome	Description
Adhered	Metrics that meet the evaluation criteria.
Not Adhered	Metrics that don’t meet the evaluation criteria.
N/A	Metrics marked as not applicable.

Evaluation Details Displays evaluation results for each metric.

Field	Description
Metric	Evaluation criterion used during the audit.
Metric Type	Evaluation method associated with the metric.
Evaluation Outcome	Result recorded for the metric.
Auditor	Users who completed the evaluation.

Evaluation Outcomes

Outcome	Description
Adhered	The interaction meets the required standard.
Not Adhered	The interaction doesn’t meet the required standard.
N/A	The metric doesn’t apply to the interaction.

Disputed By Details

This section shows disputes raised for evaluation results. It appears when an auditor disputes one or more metrics.

Field	Description
Disputed By	Name of the user who raised the dispute.
Metric	Metric included in the dispute.
Metric Type	Evaluation method associated with the metric.
Outcome	Result associated with the disputed metric.
Auditor	User who submitted the dispute.
Comment	Reason or notes provided for the dispute.

Re-evaluation

Displays when a dispute triggers a re-evaluation. The section includes the auditor who assigned the re-evaluation, the outcome summary, updated evaluation score, re-evaluated metrics, updated outcomes, and auditor comments.

System Assignment

Displays when workflow automation creates an audit assignment. The Allocation Assigned By field displays System for automated assignments.

​Prerequisites

​Access AI-Assisted Manual Audit

​Audit Workflow

​Save an Audit Draft

​Before You Begin

​Save a Draft

​Resume a Draft Audit

​Submit an Audit

​Before You Begin

​Procedure

​After Submission

​Edit a Completed Audit

​Before You Begin

​Edit a Completed Audit

​Edit Availability

​What Happens After You Edit

​Agent Acknowledgment and Dispute

​Handoff Conversations

​Segment Allocation

​Assigning a Handoff Conversation

​Switching Between Conversation Segments

​Per-Segment Overview and Metrics

​Audit Screen Headers

​Audit Screen Components

​Transcript Navigation

​Transcript and Recording Navigation

​Message-to-Recording Navigation

​Audit Review Tabs

​Processing Status

​Audit Screen Tabs

​Audit Tab

​Audit Progress

​Mark for Coaching

​Individual Agent Coaching

​Group of Agents Coaching

​Add New Group

​Coaching Recommendation Creation

​Supervisor View — Review Panel

​Comments & Dispute

​Dispute Resolution

​Agent View — Review Panel

​Audit Evaluation

​AI Overview

​Score Summary

​Topics and Intents

​Resolution and Sentiment

​Generated Topics

​Transcript and Timeline

​Sentiment Analysis

​Sentiment Ratio

​Sentiment Patterns

​Emotion Analysis

​Emotion Analysis

​Conversation Insights

​Agent Speech Insights

​Transcript and Timeline

​By Question (Audit)

​Evaluation Components

​AI Justification

​Dynamic By Question – Not Applicable Justification

​Timestamp Generation Rule

​Adherence Filter Status

​Audit Navigation and Keyword-based Conversation Analysis

​Omissions

​Violations

​By Playbook

​By Value

​By AI Agent

​Conversation Insights

​Agent Speech Insights

​Comments

​Adding a Message-Level Comment

​Comment Types

​Click-Through Navigation

​Near-Miss Scenarios

​Self-Assignment for Audit

​Audit Submission

​Search

​Conversation Details Tab

​Custom Fields

Prerequisites

Access AI-Assisted Manual Audit

Audit Workflow

Save an Audit Draft

Before You Begin

Save a Draft

Resume a Draft Audit

Submit an Audit

Before You Begin

Procedure

After Submission

Edit a Completed Audit

Before You Begin

Edit a Completed Audit

Edit Availability

What Happens After You Edit

Agent Acknowledgment and Dispute

Handoff Conversations

Segment Allocation

Assigning a Handoff Conversation

Switching Between Conversation Segments

Per-Segment Overview and Metrics

Audit Screen Headers

Audit Screen Components

Transcript Navigation

Transcript and Recording Navigation

Message-to-Recording Navigation

Audit Review Tabs

Processing Status

Audit Screen Tabs

Audit Tab

Audit Progress

Mark for Coaching

Individual Agent Coaching

Group of Agents Coaching

Add New Group

Coaching Recommendation Creation

Supervisor View — Review Panel

Comments & Dispute

Dispute Resolution

Agent View — Review Panel

Audit Evaluation

AI Overview

Score Summary

Topics and Intents

Resolution and Sentiment

Generated Topics

Transcript and Timeline

Sentiment Analysis

Sentiment Ratio

Sentiment Patterns

Emotion Analysis

Emotion Analysis

Conversation Insights

Agent Speech Insights

Transcript and Timeline

By Question (Audit)

Evaluation Components

AI Justification

Dynamic By Question – Not Applicable Justification

Timestamp Generation Rule

Adherence Filter Status

Audit Navigation and Keyword-based Conversation Analysis

Omissions

Violations

By Playbook

By Value

By AI Agent

Conversation Insights

Agent Speech Insights

Comments

Adding a Message-Level Comment

Comment Types

Click-Through Navigation

Near-Miss Scenarios

Self-Assignment for Audit

Audit Submission

Search

Conversation Details Tab

Custom Fields