AI sales coaching glossary.

The ability to recognise, measure, and deliberately control the emotional signals that influence how decisions are made. In sales, EDI determines whether a rep's message builds buyer trust or erodes it. EchoDepth trains EDI through real-time emotional feedback during practice sessions. Coined by Cavefish Ltd.

A standardised taxonomy for decomposing facial expressions into their constituent muscle movements, developed by Paul Ekman and Wallace Friesen. FACS identifies 44 discrete Action Units that can be reliably observed and measured. FACS is the most rigorous publicly validated system for facial expression analysis and forms the foundation of EchoDepth's emotional detection engine.

An individual muscle movement in the face, as defined by the Facial Action Coding System. For example, AU6 is the cheek raiser, AU12 is the lip corner puller. Combinations of Action Units produce recognisable emotional expressions. EchoDepth analyses 44 Action Units simultaneously in real time.

Valence-Arousal-Dominance model. A three-dimensional framework for representing emotional state. Valence reflects the positive or negative quality of the state. Arousal reflects intensity or activation level. Dominance reflects perceived control and confidence. EchoDepth maps Action Unit patterns to VAD space to produce nuanced emotional state profiles.

The positive or negative quality of an emotional state in the VAD model. High valence = positive (confidence, warmth, enthusiasm). Low valence = negative (anxiety, frustration). Valence is a primary driver of buyer perception.

The activation or intensity level of an emotional state in the VAD model. High arousal can be either positive (enthusiasm) or negative (panic). EchoDepth uses VAD to distinguish between these states that have the same arousal level but very different buyer impact.

The perceived control and authority dimension of the VAD model. High dominance = confident, authoritative, in control. Low dominance = uncertain, deferring. Dominance is the dimension buyers are most sensitive to during initial trust formation.

AI that analyses multiple input types simultaneously. EchoDepth is multimodal: it analyses facial video (44 Action Units), vocal audio (prosody, pace, tone), and linguistic patterns at the same time, giving a complete picture of emotional delivery.

The composite impression a sales rep makes on a buyer — encompassing confidence, warmth, authority, and credibility — as perceived through emotional expression, vocal delivery, and physical behaviour. Sales presence is distinct from product knowledge. EchoDepth trains it specifically.

An EchoDepth metric reflecting a rep's ability to maintain stable, high-quality emotional performance under pressure — specifically during objection handling. Trained through repeated avatar-led pressure scenarios that trigger genuine emotional responses.

The patterns of rhythm, stress, pace, and intonation in speech. Prosody carries significant emotional signal that buyers respond to before they process word content. EchoDepth analyses prosody alongside facial Action Units for a complete delivery picture.