> Source: https://builder-docs.ema.ai/agent-qa
> Title: Agent QA

# 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](/legacy-docs/agent-qa/core-concepts), then [2\. Setting Up Agent QA](/legacy-docs/agent-qa/setup), then [3\. Imports, Genesys, and Agent Mapping](/legacy-docs/agent-qa/imports)

**QA Manager** or **Interaction Analyst** running day-to-day QA operations

[4\. Reviewing Interactions](/legacy-docs/agent-qa/audit), [6\. Metrics Dashboard](/legacy-docs/agent-qa/metrics), [7\. Insights Dashboard](/legacy-docs/agent-qa/insights)

**Supervisor** or **Team Lead** coaching agents

[5\. Understanding QA Scores](/legacy-docs/agent-qa/scores), [7\. Insights Dashboard](/legacy-docs/agent-qa/insights)

**Contact Center Agent** viewing your own results

[10\. For Agents: Viewing Your Own Results](/legacy-docs/agent-qa/agent-view)

## Section Contents

Section

Description

[Core Concepts](/legacy-docs/agent-qa/core-concepts)

Pipeline, key terms, evaluation mechanisms, the daily QA loop, supported languages

[Setting Up Agent QA](/legacy-docs/agent-qa/setup)

Prerequisites, AI Employee creation, Auto-Learning, knowledge base, integrations, contact reasons, permissions, first call

[Imports, Genesys, and Agent Mapping](/legacy-docs/agent-qa/imports)

Bring conversations in -- Genesys Cloud, bulk file upload, re-runs, and agent mapping

[Reviewing Interactions (Audit Tab)](/legacy-docs/agent-qa/audit)

Navigation, filters, sorting, scorecard details, transcript, strengths, opportunities, CSAT analysis

[Understanding QA Scores](/legacy-docs/agent-qa/scores)

Weighted scoring formula, score ranges, critical parameters, auto-fail, N/A handling

[Metrics Dashboard](/legacy-docs/agent-qa/metrics)

Overview KPIs, available analytics charts, filters, reading the charts

[Insights Dashboard](/legacy-docs/agent-qa/insights)

Five insight categories, thresholds, detail views, effective use

[Feedback and Continuous Learning](/legacy-docs/agent-qa/feedback)

Submitting feedback, moderation, improvement suggestions, applying changes

[Managing QA Parameters](/legacy-docs/agent-qa/parameters)

Editable fields, when to re-run Auto-Learning, training material generation

[For Agents: Viewing Your Own Results](/legacy-docs/agent-qa/agent-view)

Agent self-service guide for viewing evaluations and scores

[Roles and Permissions](/legacy-docs/agent-qa/roles)

Four roles, permissions matrix, permission codes

[Audio Ingestion API](/legacy-docs/agent-qa/api-audio-ingestion)

Upload audio recordings (.mp3/.wav) for processing by Agent QA.

[Transcript Ingestion API](/legacy-docs/agent-qa/api-transcript-ingestion)

Upload pre-existing transcripts (JSON/XML/HTML) when audio is unavailable.

[Daily Data Export API](/legacy-docs/agent-qa/api-daily-export)

Pull nightly QA results, scorecards, and insights as JSONL with a manifest.

[CSAT Ingestion API](/legacy-docs/agent-qa/api-csat-ingestion)

Upload a customer satisfaction score or free-text feedback for a previously ingested call.

[Glossary](/legacy-docs/agent-qa/glossary)

Definitions of all Agent QA terms