Bodyswaps logo on orange background

Job Interview Roleplay

Tutor notes

Estimated module duration: 10-30 minutes (dependent on customisation)

Interviewing well is a valuable skill, and like any skill, mastery takes practice. But getting that practice in with real interviews takes time, which could mean missed opportunities and a long job hunting journey. Honing that skill before you get to the interview room means that you come to the table confident, prepared, and able to handle anything they might throw at you.

Our Job Interview Roleplay is a fully customisable, AI-powered roleplay simulation, in which learners can practice virtual interviews for almost any position they can think of. It’s a psychologically safe space for learners to face the pressure of a job interview, without risking real rejection.

At the end of the simulation, learners receive tailored feedback to discover where they did well and where they have room to improve their interviewing skills.

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 & environments
Customisation
Roleplay experience
Analytics
Video previews

Key learner outcome and goals

Learning outcome

Practise your interview technique to build confidence and competence.

Learning goals

  • Give clear, professional answers to interview questions
  • Demonstrate open body language and good eye contact to project confidence
  • Use structuring techniques like CAR and STAR to craft effective answers
  • Be prepared to handle follow-up questions and requests for more information

Customisation

The interview can be customised in BSGO to best suit the needs of educators and learners. Aspects that can be customised include:

- Job role: what position is the learner interviewing for?
- Company: who is hiring?
- Job description: what are the requirements and responsibilities of the role? Note that this is used by the LLM (large language model) to generate interview questions. You can write your own, upload a PDF or leave it blank if you wish to set the questions yourself.
- Questions to be asked: you can write your own, or have the LLM generate questions based on the job role and description.
- Number of questions: how many questions should be generated or asked?
- Interviewer(s): you can select up to three interviewers, each of whom has a distinct personality and difficulty level.
- Environment: you can choose from three environments.
- Response structure: you can choose to have the learner’s responses assessed by how well they meet the CAR or STAR structures.
- Allow help: you can choose to allow the learner to ask for help answering a particular question.
- Allow follow-up questions: should the interviewers be allowed to ask LLM-generated follow-up questions after the learner gives an answer, if they want more details?

You can also edit technical details like the activity title, description and instructions for the learner, based on how you tailor the scenario. Optionally, you can also allow the learner to set the job details, in which case they will be able to enter a job when they launch the simulation and the LLM will generate questions for it.

For a fuller explanation of these options and further help customising the scenario, click here.

Note: The prompt contains a safeguard to prevent inputting illegal, explicit or harmful jobs – it will generate questions for a barista interview instead, but as with all LLM generation, we cannot guarantee it will be perfectly effective under all circumstances. Please see the disclaimer below.

Disclaimer about AI

This Job Interview Roleplay uses an LLM to generate the virtual character’s responses, offer advice on answering questions, 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 intended to safeguard against unintended or inappropriate use, please be aware of the following limitations:

- Due to the large nature of its dataset, the LLM is prone to ‘hallucinating’, 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 interview customisation, deliberate attempts to manipulate the system, and unanticipated responses from the learner may cause unexpected 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

Leon
Leon
Virtual interviewer Leon is easy-going and won’t push a learner too hard
Kel
Kel Rosales
Virtual interviewer Kel is inquisitive and driven, and always prefers detailed answers
Cora
Cora Varney
Virtual interviewer Cora isn’t easy to please, and rarely shows any signs of approval

Environments

Small meeting room - tutor notes

Small meeting room

A small meeting room, suitable for interviews for an office-based role.

Cafe breakout - tutor notes

Café

An airy café space, suitable for interviews for a restaurant or coffee shop role.

Retail breakroom - tutor notes

Retail breakroom

A breakroom space, suitable for interviews for a retail role.

Roleplay experience

When they enter the simulator, the learner is greeted with the customised instructions in a text pop-up, offering guidance on what to expect and a chance to review the job description ahead of their interview. If no job role was set, they are prompted to enter a job role for themselves. If the interview hasn’t been customised at all, they are prompted to select one of our pre-written scenarios.

Next, it’s time for the interview. The interviewer or interviewers will introduce themselves and begin to ask questions. After each one, the learner responds in their own words. The interviewer will acknowledge the learner’s answer before asking their next question. Or, if follow-up questions have been enabled, they may occasionally ask for more details or clarification of the learner’s answers, before moving onto the next question in the set list.

Each interviewer has a predefined personality that governs how they interact with the learner. As a general rule, confident, thorough, and well-structured answers from the learner will cause the interviewers to respond positively, while careless, disrespectful or poorly-structured answers will lead to increasing disapproval.

Should the learner need help, and if it has been enabled in BSGO, they can press the ‘Help me’ button before answering a question. This generates two pieces of advice: one on how to give an answer relevant to the current question and one on how to structure their answer according to CAR or STAR, depending on which was selected when the interview was customised.

Once all questions have been asked and answered, along with any follow-up questions, the interviewers will thank the learner for their time and bring the interview to a close.

Analytics and feedback

When the interview concludes, the learner is given written feedback on the various skills they used during the interview. Feedback on their responses is LLM-generated, based on analysis of their interview skills, and feedback on their non-verbal behaviour is pre-written by our learning designers.

Each piece of feedback consists of a brief paragraph explaining where the learner did well and where they could stand to improve, backed up by quotations from their transcript.

The following skills are assessed:

- Relevance: how well the learner stayed on topic and connected their experience to the demands of the role and the questions.
- Clarity: how clearly the learner spoke and how easy the interviewers found it to understand their points.
- Concision: how well the learner balanced brevity and thoroughness; whether they rambled and strayed from the point or conveyed what they needed to with an economy of words.
- Confidence: whether the learner hedged their assertions with phrases like ‘I think’, or stumbled, or otherwise came across as lacking in confidence to the interviewer.
- Structure: how well the learner structured their answer according to the CAR or STAR models, whichever was selected during setup.
- Professionalism: how far the learner acted in a respectful, professional manner.
- Expanding on answers: how adroitly the learner handles follow-up questions and expands on their initial answers when the interviewers request further information.
- Eye contact (VR only): whether the learner maintained a good level of eye contact, helping to build connection and give a sense of confidence.
- Body language (VR only): whether the learner consistently used a relaxed, open posture to convey confidence and put their interviewer at ease.
- Articulation: how quickly the learner spoke, measured in words per minute, and whether they spoke too fast or too slow.
- Filler words: how far the learner managed to avoid using filler words in their responses.

The learner can also view a transcript of their interview alongside the feedback, to prompt self-reflection on where they succeeded and where they fell short.

All of this information is made available on BSGO in the learner report, where it can be filtered or downloaded as a PDF.

Exit survey

Purpose

Assess the effectiveness of the training itself

Location

N/A

Characters

N/A

Journal

N/A

Duration

1:00

*Varies depending on the learner's choices and interactions.

Before the learner leaves the module, they are asked to complete a short survey about their experience.

This data helps us to assess the effectiveness of our product and identify any areas that need improvement. Clients also find it beneficial when assessing ROI. 

They are asked to mark whether they agree or disagree with the following statements, on a 10 point scale:

  • I would recommend this experience to others. 
  • The experience helped me identify elements of my interview technique I could improve upon.
  • I now have a better understanding of how to handle interview questions.

Video example: University admissions

Video example: Retail Assistant

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

hello@bodyswaps.co
bodyswaps.co