> Source: https://builder-docs.ema.ai/agent-qa/glossary
> Title: Glossary

# Glossary

Term

Definition

**Action Based Rule**

A QA parameter that verifies actions in external systems (CRM, ticketing).

**Agent (Platform)**

A modular AI component within Ema that performs a specific task (transcription, categorization, rule validation).

**Agent (Contact Center)**

A human customer service representative whose calls are evaluated by Agent QA.

**AI Employee**

A configured workflow on the Ema platform. Agent QA is an AI Employee template. Also called a "persona" internally.

**Auto-Fail**

When a critical parameter fails, the interaction automatically receives a score of 0.

**Auto-Learning**

Batch calibration that generates and refines parameter instructions from golden data.

**Call Driver**

The L3 (most specific) level of contact reason categorization.

**Channel Map**

A JSON mapping of audio channels to speakers (Agent/Customer) in stereo recordings.

**Continuous Learning**

Incremental improvement of evaluation accuracy through moderated feedback.

**Contact Reason**

Three-level categorization of why customers call: L1, L2, L3/Call Driver.

**Critical Parameter**

A parameter where failure automatically scores the interaction at 0.

**CSAT**

Customer Satisfaction -- predicted by AI analysis of the interaction.

**Dead Air**

Silence during a call where neither party is speaking. Measured in seconds.

**Diarization**

Separating audio into segments by speaker (Agent vs. Customer).

**EmaFusion™**

Ema's multi-model AI architecture that selects the optimal LLM for each task.

**Golden Dataset**

Call recordings with verified human evaluations used for Auto-Learning calibration.

**GWE (Generative Workflow Engine)**

Ema's orchestration layer coordinating multiple agents in a workflow.

**Insight**

A pattern identified across multiple interactions. Types: Strength, Opportunity, Bug, Feedback, Competitor.

**Interaction**

A single customer service call processed by Agent QA.

**Knowledge Base**

Documents (policies, procedures, FAQs) that Ema references for Knowledge Verified rules.

**Knowledge Verified Rule**

A parameter that cross-references transcript content against knowledge base documents.

**N/A (Not Applicable)**

Evaluation result indicating the parameter does not apply to a particular call. Excluded from scoring.

**Non-Resolution Reason**

Categorization of why a customer's issue was not resolved (L1, L2).

**Parameter**

A single QA evaluation criterion with pass/fail criteria and a weight. Also called a "rule."

**PII (Personally Identifiable Information)**

Sensitive data detected and masked. Redacted by default via two independent passes, so PII missed by one pass can still be caught by the other.

**QA Score**

Weighted overall score (0-100). Formula: (passed\_weight\_sum / applicable\_weight\_sum) x 100. Set to 0 on auto-fail.

**QA Form**

CSV file defining evaluation parameters, criteria, weights, and criticality.

**Resource ID**

External identifier for a call. Corresponds to `resource_id` in the API and `UCID` in golden data.

**Scorecard**

Summary view of all parameter evaluations for a single interaction.

**Sentiment Analysis**

AI analysis of customer emotional state: POSITIVE, NEGATIVE, or NEUTRAL.

**Transcript Only Rule**

A parameter evaluated based solely on conversation content.

**UCID (Unique Call Identifier)**

Unique identifier for each call recording. Matches `resource_id` in the API.

**Verbatim**

A direct transcript quote supporting an evaluation rationale.

**Weight**

Numerical value indicating a parameter's importance in scoring. Must be > 0.

**Workflow Builder**

Visual interface for creating and modifying AI Employee workflows.