Bodyswaps logo on orange background

Debating - AI Roleplay

Tutor notes

This debating roleplay simulator offers learners an opportunity to refine their critical thinking and argumentation skills in a customisable environment. By engaging with an AI-powered debating opponent, learners practice not only constructing logical arguments, but also maintaining emotional composure, managing disagreements and actively adapting their tone and approach, based on the flow of the debate.

This roleplay experience fosters critical soft skills such as: good listening, emotional regulation and persuasive communication. Additionally, by receiving personalised feedback on their performance, learners can identify areas for growth, without the added pressure or anxiety often associated with live debates.

About this resource

This document provides an overview of each of the learning activities featured in this programme, including:
Key learner outcome and goals
Characters and environments
Customisation
Roleplay experience
Analytics
Video previews

Key learner outcome and goals

Learning outcome

Demonstrate effective argumentation and interpersonal communication skills

Learning goals

  • Maintain respectful communication by acknowledging opposing views and managing emotional responses
  • Construct clear, evidence-based arguments that follow a logical structure
  • Challenge inconsistent and unsupported claims
  • Offer viewpoints that are free from overgeneralisations and discrimination
  • Communicate with good eye contact and open body language

Disclaimer about AI

This roleplay simulator uses an LLM (large language model) to generate the virtual character’s responses, guide the direction of the conversation, and write personalised feedback for the learner. While we have designed the prompts around the learning outcomes and goals of this simulator, and with strict conversation boundaries that prevent unintended or inappropriate use, please be aware of the following limitations:

  • Due to the large nature of its dataset, the LLM is prone to ‘hallucinate’, meaning it may generate information that appears factual but is incorrect, misleading, or entirely fabricated.
  • It is impossible to predict everything that users may feed into the customisation fields and everything that they may say in the conversation. Therefore, unintended or misguided uses of the conversation customisation, deliberate attempts to manipulate the system, and repeatedly unpredictable answers from the learner may cause unanticipated outputs from the LLM that are beyond our control.

In short, please be aware that we cannot guarantee all AI-generated content will be accurate, appropriate, or aligned with educational objectives in all circumstances.

We appreciate any feedback about the performance of our simulators. We work hard to design and improve our LLM-based roleplays to give you a personalised, yet safe and impactful learning experience.

Characters and environment

Debate with May or Leonard in an auditorium.
85_May_Avatar_Female (3)
May
public_forum_3840x2160_1 (3)
Debating public forum
0075_Leonard_Avatar_Male_4
Leonard

Customisation

The debate topic and the AI debate opponent in this roleplay can be customised in BSGO for a unique and personalised experience: 

  • Debate topic: set any subject relevant to your curriculum or learning objectives
  • Positions: define both the learner's stance and the avatar's opposing viewpoint
  • Avatar: choose between May and Leonard to match your scenario
  • Avatar personality: customise the avatar's background, interests, speaking style and current mood to create a realistic debate
  • Difficulty level: adjust between "Easy" (basic arguments, simpler language) and "Difficult" (complex reasoning and domain-specific terminology)
  • Debate length: control the number of exchanges in the debate
  • Transcript submission: toggle to choose if learners must submit their debate transcript for instructor review
You can also edit technical details like the activity title and description, based on how you tailored the scenario. 
AI Roleplay Guide

Roleplay experience

The debating roleplay begins with a customised text panel which introduces the learners to their assigned debate topic and position. They then enter a virtual auditorium and face their fellow debater.

The debate unfolds in a structured back-and-forth exchange. The avatar opens with arguments supporting its assigned position, prompting the learner to respond and the conversation evolves from there. As it progresses, the avatar’s responses dynamically adapt, based on the learner’s input. Learners practice real-time adaptation too, as they need to refine their approach each time their views are challenged. If their arguments are baseless or simply not strong enough, the avatar will become progressively less inclined to engage in the debate. If the learner continuously uses foul language or displays aggressive or negative behaviours, their opponent will shut the debate down completely and the simulation will end.

Throughout the debate, learners test their ability to construct strong and relevant counterarguments, manage opposing views and maintain a composed demeanor. The avatar maintains focus on the central topic, while implicitly encouraging learners to develop flexibility in their communication style – an essential component of persuasive dialogue. According to the selected difficulty level, learners strengthen their ability to think critically and challenge, rather than dismiss, their opponent’s views.

On the second to last exchange, the avatar prompts the learner for their final statement, before bringing the debate to a close. Learners can then view the AI-powered, personalised feedback on their performance.

Analytics and feedback

Throughout the debate the AI continuously assesses six critical aspects of the learner’s performance:

  • Respectful communication: evaluates the learner's ability to maintain composure, even during disagreements, including their use of appropriate language, acknowledgment of opposing viewpoints and avoidance of personal attacks or dismissive rhetoric
  • Clarity of arguments: measures how effectively the learner structures and articulates their position, including logical flow and supporting evidence
  • Mistakes in reasoning: identifies any logical fallacies, unsupported claims, contradictions, or other flaws in the learner's arguments
  • Discrimination and judgment: analyses content for biased language, stereotyping, overgeneralisations, or other forms of discriminatory expression
  • Eye contact: evaluates the learner’s ability to maintain steady and balanced eye contact with both their opponent and the audience to indicate engagement and attentiveness
  • Body language: tracks the learner’s use of non-verbal cues, including posture and hand gestures, to gauge confidence and focus, or pick up on any signs of nervousness or disengagement

In their personalised feedback, learners can identify their strengths and areas for improvement across all of these dimensions. Learners can also review the full conversation transcript to reflect on how their responses and debating style influenced the outcome of the simulation.

White Bodyswaps logo on blue background
31 New Inn Yard, EC2A3EY, London
+44(0)79 1773 5078

hello@bodyswaps.co
bodyswaps.co