Quality Assessment

Where Assessments Can Be Found

Assessments can be accessed directly in the ticket view: the assessment button in the ticket details bar opens the work items of the ticket with all related assessments. The button is only visible if the logged-in user has at least one of the permissions to view assessments (see below). If a ticket has no work item yet, the button is greyed out.

QA Control Center

The QA Control Center gives an overview of all assessments. It can be reached in the sidebar under Control Center → QA Control.

It shows the quality results at a glance, and individual assessments can be opened directly:

• Overview – average quality score, number of assessments and SLA compliance
• Score trend – development of the quality score over time
• Composition – assessments by state, assessment type and score distribution
• Breakdowns – quality scores by scorecard, team, member and channel
• Assessments – list of individual assessments to open and edit

The view can be filtered by period, channel, scorecard, agent, team and state.

Access requires the permission "Quality Control Centre access".

Scorecards are managed under Settings → User Management → Quality Scorecards.

Reviewing and Completing an Assessment

1. Open the assessment – via the assessment button in the ticket or via the list in the QA Control Center.
2. Check the criteria – if needed, adjust the score and Reason of a criterion. The criterion is then considered "Human-verified".
3. Add to the summary – adjust the summary created by the AI via Edit summary.
4. Mark as verified – completes the review. The state changes to "Supervisor reviewed".
5. Mark as discussed with assessee – after the conversation with the assessed employee.

The assessment shows the Date of supervisor assessment and the Date of discussion with assessee.

Delete assessment removes an assessment; this requires the permission "Delete quality assessments". Only users with one of the permissions "Perform quality assessments (team members)" or "Perform quality assessments (all)" can change an assessment – for the summary, "Edit quality assessment summary" is also required. Everyone else can only view the assessment.

Permissions

The permissions for assessments and scorecards are found in the role editor in the group Quality Management:

The permissions for the QA Control Center are found in the group Data and reports:

How Assessments Are Created

Assessments are not created manually. Every minute, Enneo automatically checks whether there are new work items in which an employee wrote a reply or handled a call and that have not been assessed yet. An assessment is created for every active scorecard that applies to such a work item.

There can be several assessments per work item – one for each scorecard whose assignment rules apply.

Right afterwards, the AI starts the pre-assessment.

AI Processing

The AI receives the following as the basis for its assessment:

• The ticket's message flow – from the first customer contact to the last agent reply (including internal notes)
• The scorecard with all categories, criteria and assessment prompts for the AI
• Details of the work item – time tracking, AI agents used, degree of automation
• The customer experience – SLA compliance, CSAT

The AI assesses all criteria for which Auto-generate by AI is enabled and returns a score and a reason for each criterion. It then writes a summary.

AI-assessed criteria get the state "AI-Generated". Criteria without AI assessment remain "Unscored" and must be assessed manually.

Assessment Data

An assessment contains:

• Categories and criteria – with score, reason and assessment state per criterion
• Overall result – points achieved, maximum possible points and percentage
• AI summary – free text, written by the AI
• Supervisor summary – free text, entered manually via "Edit summary"
• Date of supervisor assessment and Date of discussion with assessee – for documentation purposes
• Time tracking – handling time (segments, after-call work)
• AI usage – which AI agents were involved, degree of automation
• Customer experience – SLA status, whether the ticket was reopened, CSAT result
• Change history – complete log of all changes (score, reason, state, who changed what and when)

Score Calculation

How Is the Percentage Calculated?

The percentage is the points achieved divided by the maximum possible points of the scored criteria. A criterion with 0 points counts as scored.

Unscored criteria are not counted. This allows a valid partial assessment when individual criteria cannot be judged due to missing data.

Knockout Logic and Its Effect on the Score

Criteria can be marked as knockout criteria for the category or for the whole assessment (in the scorecard: Make-or-break for category or Make-or-break for assessment).

• Category knockout: If such a criterion scores 0 points, all points of the category are set to 0 – regardless of other criteria in the same category.
• Assessment knockout: If such a criterion scores 0 points, the result of the whole assessment is set to 0.

The knockout logic is applied every time the total is recalculated, i.e. after every AI assessment and every manual change.

Workflow States

Assessments go through a defined process:

Automatic reset: If a supervisor makes changes after completing the review ("Supervisor reviewed") or after the feedback conversation ("Discussed with assessee"), the state automatically changes back to "Review in progress". Entered assessment and discussion dates are kept.

Criterion States

Each criterion within an assessment has its own state:

Context Data in the Assessment

Time Tracking

The assessment contains the time tracking data of the work item: total handling time, after-call work and individual time segments with the actions performed. This data comes from the employee's work item and is captured when the assessment is created.

AI Usage

For each work item, it is documented which AI agents were involved and how highly automated the handling was. This information serves as context for the quality assessment – fully automated work items need to be assessed differently from manually handled ones.

Customer Experience

The assessment contains information on SLA compliance (whether the deadline was met, how many seconds after the deadline the ticket was closed), whether the ticket was reopened, and the CSAT result (customer satisfaction survey), if available. This data provides objective quality signals independent of the scorecard assessment.

Export

Quality assessments can be exported under Settings → Advanced Settings → Data Export with the export type Quality Assessments as XLSX, CSV or JSON. This requires the permission "View quality assessments (all)". The export contains all assessment data including scores, reasons, time tracking and customer experience and is suitable for external reporting or analysis in BI tools.

Best Practices

• Use the change history: The complete log of all score and state changes makes assessments traceable. When questions come up, you can see what the AI originally assessed and what was adjusted manually.
• Maintain the supervisor assessment and discussion dates: These fields are essential for meaningful reporting – without them, assessment periods cannot be analysed correctly.
• Treat the AI summary as a starting point: The AI summary is not a final assessment but a structured starting point for the supervisor review. It should not be used unchecked as the basis for a feedback conversation.
• Monitor the error state: Assessments in the state "Error" are not retried automatically. They should be checked regularly to avoid gaps in reporting. The Run Assessment button restarts a failed assessment. Once it has been reviewed or discussed, this is no longer possible.