Agent Model

How communication research shapes every agent interaction

Eva Communication Coach demonstrates a practical idea: an agent should not only answer words, but also pay attention to how interaction unfolds. The core model builds on research in audiovisual prosody, spoken dialogue, feedback, turn-taking, communication problems and emotion. This interaction model is used across all Agent Interaction Lab agents, adapted to each agent's role and purpose.

See how agents adapt View research

Two roles

Eva Communication Coach first talks with you, then analyses the interaction

During the live minute, Eva Communication Coach's first task is simple: have a short, natural dialogue. She responds to the situation you describe, asks follow-up questions and adapts her tone when clear affect cues appear.

After the interaction, Eva Communication Coach switches role. She analyses the transcript for moments where communication may become easier, harder, more emotional, less clear or more repair-oriented. That second role is where the research categories become visible to the user.

What Eva Communication Coach Watches For

A practical translation of audiovisual prosody and interaction research

The current demo is text-first, but the conceptual model comes from spoken, audiovisual interaction. Eva Communication Coach watches how people show understanding, hesitation, emotion, emphasis, repair and turn completion. She treats feedback words, pauses, overlap, uncertainty markers, emotionally loaded phrases and finality cues as small interaction signals. During the conversation those signals can change her wording, pace and follow-up question; after the conversation they become visible as practical feedback categories.

Feedback

Eva Communication Coach looks for signs that people understand each other, need clarification, correct themselves, ask for grounding or show that a misunderstanding may be forming.

Turn-taking

Eva Communication Coach pays attention to pauses, overlap, interruptions and moments where someone may still be searching for words rather than handing over the turn.

Emotion and emphasis

Eva Communication Coach reads affective language, emphasis markers and emotionally loaded phrases as cues for adapting tone, pace and wording without turning that into a diagnosis.

Repair

Eva Communication Coach treats corrections, rephrasing, explicit disagreement and phrases such as "you do not understand me" as repair moments where shared understanding needs attention.

Finality cues

Eva Communication Coach looks for language and timing cues that suggest whether someone is finished, wants to continue, or needs a little more time before the agent responds.

Affect adaptation

Eva Communication Coach can slightly shift tone, speed and wording when joy, sadness, stress, anger, confusion or relief appear, while keeping the conversation focused on the situation described.

Uncertainty

Eva Communication Coach treats hesitation, mixed wording and uncertainty markers as cues to slow down, clarify and avoid overconfident conclusions.

Grounding

Eva Communication Coach looks for moments where examples, shared references or concrete next steps can make an abstract concern easier to discuss.

Conversation trouble

Eva Communication Coach notices when the interaction itself becomes the topic, such as confusion, frustration, repetition or a request to change approach.

Emotion Model

From emotion words to conversational adaptation

Eva Communication Coach uses a compact affect layer inspired by universal emotion families such as joy, sadness, anger, fear, disgust and surprise. For conversation, she also recognises broader affect cues such as stress, overwhelm, shame, confusion, relief, anxiety, irritation and loneliness.

This is not a diagnosis layer. It is a communication layer. When someone says "this is getting too much", Eva Communication Coach can become calmer and help narrow the next step. When someone says "you do not understand me", she treats it as a repair signal.

Research foundation

Research on interaction, emotion and responsive dialogue

The model combines research on audiovisual prosody, spoken feedback, turn-taking, communication repair and emotion with reflective listening and contextual conversational AI. Together, these sources inform how an agent can notice interaction signals and respond without labelling or diagnosing the user.

View research