Reviewing Interactions (The Audit Tab)
The Audit tab is where you review individual evaluated interactions. This is the starting point for daily QA work -- finding calls to review, examining scorecards, reading transcripts, and submitting feedback.
3.1 Navigate the Audit Tab
- Log in to Ema at app.ema.co
- Navigate to your Agent QA AI Employee
- Click the Audit tab
Each row in the interaction list displays:
| Field | Description |
|---|---|
| Interaction Details | Combined column showing the Interaction ID (resource_id, truncated to first 12 characters with # prefix) and the Agent ID displayed below it |
| Duration | Call length in seconds |
| QA Status | The current state of the evaluation |
| QA Score | Overall score out of 100. If the score has not been computed yet, it displays as "--". |
| Date | When the call took place |
QA Status Values
| Status | What It Means |
|---|---|
| QA completed | Evaluation is finished and the score is available. Click in to see full details. |
| QA in progress | The system is still processing this interaction. Check back shortly. |
| QA failed | Something went wrong during processing. Check audio quality, file format, or contact your administrator. |
3.2 Filters and Sorting
Available Filters
| Filter | Description |
|---|---|
| Date range | Custom date range (UTC). Presets: Today, Last 7 Days, Last Week, Last 14 Days, Last 30 Days, Last Month, or custom range. |
| Agent | Dropdown to select a specific agent or view all agents. |
| Interaction ID | Text search field to find a specific call by resource ID (UCID). |
| QA Status | Filter by evaluation status. |
| QA Score | Filter by preset score bands: Auto-fail (0), Low (1-50), Medium (51-75), High (76-100). |
Sorting Options
| Sort By | Directions |
|---|---|
| Call Date (default) | Ascending or Descending |
| Call Length | Ascending or Descending |
Pagination
Results display 25 interactions per page. Navigation uses token-based pagination.
3.3 View Interaction Details
Click View Details on any interaction to open the detailed view with the following tabs:
Scorecard Tab
The core evaluation view. A summary bar at the top shows the total parameter count with Pass and Fail totals.
| Field | Description |
|---|---|
| Result | Color-coded badge -- Pass (green), Fail (red), or N/A (gray) |
| Parameter name and category | What was being evaluated and which group it belongs to |
| Pass/Fail instruction | The evaluation criteria used for this parameter |
| Rationale | Detailed, plain-language explanation of why the parameter passed or failed. This is the most important field for understanding a score. |
| Verbatims | Click the "Source" accordion to expand and see the exact transcript excerpts used as evidence |
Transcript Tab
Full conversation text with speaker labels (Agent/Customer) and timestamps.
The Transcript tab does not currently have an in-panel search feature.
Strengths Tab
Positive agent behaviors identified during the interaction.
| Field | Description |
|---|---|
| Driver | The positive behavior identified (e.g., "Clear policy explanation"), displayed as bold title |
| Category | The broader behavioral category (e.g., "Communication Skills"), displayed as a badge |
| Justification | Why this was identified as a strength, labeled "Key insight" in the UI |
Opportunities Tab
Areas for improvement with coaching recommendations.
| Field | Description |
|---|---|
| Driver | The issue identified (e.g., "Did not confirm customer understanding"), displayed as bold title |
| Category | The broader behavioral category (e.g., "Active Listening"), displayed as a badge |
| Justification | Why this was identified as an opportunity and what could have been done differently |
CSAT Analysis Tab
CSAT Analysis data is computed in the backend and will appear in the evaluation details view in a future release.
Planned fields when implemented:
| Field | Values | Description |
|---|---|---|
| Sentiment | POSITIVE, NEGATIVE, NEUTRAL | Overall customer sentiment |
| Resolution Status | RESOLVED, NOT_RESOLVED | Whether the customer's issue was resolved |
| Contact Reason | L1, L2, L3 hierarchy | Why the customer called |
| Non-Resolution Reason | L1, L2 hierarchy | Why the issue was not resolved (only populated when not resolved) |
Additional Data
Agent Talk Time, User Talk Time, and Dead Air are computed in the backend and stored in the database, but are not currently displayed in the evaluation details drawer in the UI.
| Field | Description |
|---|---|
| Agent Talk Time | How much of the call the agent was speaking |
| User Talk Time | How much the customer was speaking |
| Dead Air | Periods of silence during the call |
Exporting Reports
Export functionality (Coaching Insights DOCX, Golden Data Excel, Transcription .txt) is not yet available in the production Audit tab interface. These features are planned for a future release.