Agent QA
Agent QA is an AI Employee on the Ema platform that evaluates customer service voice interactions against your organization's quality standards -- automatically, at scale, and with consistent criteria.
Instead of manually reviewing a small sample of calls, Agent QA processes every interaction and produces:
- QA Scores -- A weighted score from 0 to 100 for each interaction
- Scorecards -- Parameter-by-parameter Pass/Fail results with detailed reasoning and transcript evidence
- Analytics Dashboards -- Trends across agent performance, contact reasons, resolution rates, and sentiment
- Coaching Insights -- AI-identified patterns including agent strengths, improvement areas, product bugs, and competitive intelligence
- Real-Time Transcription -- Live speech-to-text with contextual knowledge base recommendations during active calls
This guide covers everything from initial setup to daily operations, score interpretation, agent self-service, and technical integration.
Who This Guide Is For
| Role | Start Here |
|---|---|
| Platform Administrator setting up Agent QA for the first time | 1. Core Concepts, then 2. Setting Up Agent QA |
| QA Manager or Interaction Analyst running day-to-day QA operations | 3. Reviewing Interactions, 5. Metrics Dashboard, 6. Insights Dashboard |
| Supervisor or Team Lead coaching agents | 4. Understanding QA Scores, 6. Insights Dashboard |
| Contact Center Agent viewing your own results | 9. For Agents: Viewing Your Own Results |
Section Contents
| Section | Description |
|---|---|
| Core Concepts | Pipeline, key terms, evaluation mechanisms, the daily QA loop, supported languages |
| Setting Up Agent QA | Prerequisites, AI Employee creation, Auto-Learning, knowledge base, integrations, contact reasons, permissions, first call |
| Reviewing Interactions (Audit Tab) | Navigation, filters, sorting, scorecard details, transcript, strengths, opportunities, CSAT analysis |
| Understanding QA Scores | Weighted scoring formula, score ranges, critical parameters, auto-fail, N/A handling |
| Metrics Dashboard | Overview KPIs, available analytics charts, filters, reading the charts |
| Insights Dashboard | Five insight categories, thresholds, detail views, effective use |
| Feedback and Continuous Learning | Submitting feedback, moderation, improvement suggestions, applying changes |
| Managing QA Parameters | Editable fields, when to re-run Auto-Learning, training material generation |
| For Agents: Viewing Your Own Results | Agent self-service guide for viewing evaluations and scores |
| Roles and Permissions | Four roles, permissions matrix, permission codes |
| Audio Ingestion API | Upload audio recordings (.mp3/.wav) for processing by Agent QA. |
| Transcript Ingestion API | Upload pre-existing transcripts (JSON/XML/HTML) when audio is unavailable. |
| Daily Data Export API | Pull nightly QA results, scorecards, and insights as JSONL with a manifest. |
| CSAT Ingestion API | Upload a customer satisfaction score or free-text feedback for a previously ingested call. |
| Glossary | Definitions of all Agent QA terms |