Developing an Interative AI Chatbot

DESIGN PROPOSAL FOR

Click the buttons above to test the chatbot in action.

This design proposal outlines the development of Ace, an interactive AI chatbot designed to support disengaged learners by providing simplified, accessible study assistance. Ace enables students to engage with coursework in a digital-first format.

Context of the Problem

The Problem

Many disengaged learners face significant barriers to education, including low motivation, personal challenges, and literacy difficulties that make traditional study materials overwhelming. Heavy, text-dense workbooks lead to frustration, avoidance, and disengagement, while limited digital integration fails to align with how modern students prefer to learn. Additionally, teachers struggle to provide individualized support in classrooms with diverse learning needs, leaving some students behind. Without an accessible, interactive study tool, many learners find it difficult to stay engaged, complete assessments, and build the confidence needed to succeed academically and transition into the workforce. A lack of emotional and motivational support further compounds these challenges, making it essential to develop a solution that not only aids in learning but also fosters engagement and well-being.

Aims of Ace

  • Enhance Student Engagement – Provide an interactive and accessible learning tool that keeps learners motivated.

  • Simplify Complex Information – Break down text-heavy study materials into short, easy-to-understand responses.

  • Reduce Cognitive Overload – Present bite-sized learning chunks to make studying more manageable.

  • Assist Educators – Act as a teacher’s aide, freeing up time for one-on-one student support by handling basic queries.

  • Align Learning with Digital Habits – Engage students using a format familiar to them, incorporating AI, conversational learning, and digital interaction.

Target Audience

The target audience for Ask Ace consists of disengaged young adults (aged 16-20) who face significant personal and educational barriers that hinder their ability to complete formal studies. Many struggle with low literacy, poor reading comprehension, and limited communication skills, making traditional, text-heavy learning materials overwhelming and discouraging. Additionally, mental health challenges, trauma, and unstable personal circumstances often impact their attendance, motivation, and ability to focus. These students are working toward their Certificate of General Education for Adults (CGEA) as a pathway to achieving a high school certificate equivalency. They are digital natives, often relying on social media and technology for learning and communication, yet their educational environment lacks engaging digital tools. With inconsistent classroom participation and diverse learning needs, they require a flexible, interactive, and supportive learning solution that keeps them engaged while building confidence.

The Solution

The Final Product

Ask Ace is an AI-powered chatbot built using Claude 3.5 technology on the Voiceflow platform, designed to provide interactive, accessible, and personalised study support for disengaged learners. Students interact with Ace by typing their assessment questions or study-related prompts, and the chatbot processes their input using natural language understanding, delivering clear, simplified responses directly from their learning materials. Ace helps break down complex topics, reinforces literacy skills through spelling and grammar challenges, and encourages engagement with interactive explanations. By leveraging Claude 3.5’s advanced AI capabilities and Voiceflow’s conversational framework, Ace delivers a seamless, intuitive experience, ensuring students receive timely, supportive, and structured learning assistance in a format that aligns with their digital habits and communication preferences.

Theoretical Foundations & Evidence-Based Approach

Ask Ace enhances learning and engagement by providing on-demand, AI-driven study support, making education more accessible, interactive, and student-centered. By leveraging Claude 3.5 AI on Voiceflow, Ace personalises learning through adaptive responses, allowing students to process information at their own pace, which aligns with self-regulated learning theories (Zimmerman, 2002). Ace also incorporates scaffolded learning (Vygotsky, 1978) by breaking down complex topics into simplified, step-by-step explanations, reducing cognitive overload and increasing comprehension (Sweller, 1988). The chatbot's interactive literacy exercises, such as spelling and grammar challenges, align with retrieval practice strategies (Roediger & Butler, 2011), reinforcing long-term knowledge retention. By using a digital-first approach, Ace meets students where they are most comfortable—through conversational AI—which research shows improves engagement and accessibility in education (Luckin et al., 2022).

Engagement Strategies

Ask Ace incorporates evidence-based engagement strategies to enhance student motivation, participation, and retention. By utilising conversational AI and gamification principles (Gee, 2003), Ace fosters a low-pressure, interactive learning environment, encouraging students to ask questions and receive instant feedback. The chatbot applies self-determination theory (Deci & Ryan, 1985) by promoting autonomy, allowing learners to engage at their own pace, and fostering competence through structured responses and scaffolded explanations (Vygotsky, 1978). To sustain attention and reduce cognitive overload, Ace employs microlearning techniques, breaking down complex concepts into bite-sized, easily digestible information. Additionally, Ace integrates social-emotional learning strategies (Durlak et al., 2011), identifying student frustration or disengagement and directing them toward supportive resources, including a Welfare chatbot for emotional coaching.

Design Considerations

Creating the Voice and Personality

Ask Ace was designed with a friendly, approachable, and slightly playful personality to foster student engagement and motivation while maintaining professionalism. The chatbot’s tone was carefully structured using Claude 3.5 AI on Voiceflow, ensuring responses are short, clear, and easy to understand, while keeping students on track without sounding overly authoritative. Research suggests that conversational AI with a supportive, non-judgmental tone can enhance engagement and reduce anxiety in learning environments (Colby, 2022). To achieve this balance, we developed a custom language prompt that directs Ace to communicate like a helpful mentor—casual but not childish, structured but not rigid. Additionally, Ace integrates emojis and light humor to create a more engaging and relatable experience without compromising academic integrity. Given that many learners struggle with authority figures in traditional education settings, Ace was designed to motivate rather than instruct, offering encouragement, constructive feedback, and redirection when needed.

Recognising the LLN Deficiencies in Learners

Ask Ace was designed to intelligently recognise spelling mistakes, grammatical errors, and tone inflections in user input, ensuring that students receive accurate, supportive responses even when their queries are imperfect. By leveraging Claude 3.5 AI on Voiceflow, Ace is capable of interpreting misspelled words and contextually correcting them, allowing learners with low literacy skills to still engage effectively without frustration. Similarly, Ace detects grammatical inconsistencies, such as verb tense errors or sentence structure issues, and provides constructive feedback rather than simply pointing out mistakes. Beyond syntax, Ace can also identify tone inflections, such as frustration, confusion, or disengagement, prompting it to adjust its responses accordingly—offering encouragement, simplification, or even suggesting a break if needed. Research shows that AI-powered language models that adapt to user input create a more inclusive and personalized learning experience (Luckin et al., 2022).

Adding Jokes, Riddles and Humour

Integrating jokes, riddles, and light humor into Ask Ace was a deliberate strategy to make the chatbot feel more engaging, approachable, and enjoyable for students, rather than just a strict academic tool. Research highlights that humor in education can reduce anxiety, increase motivation, and improve information retention (Banas et al., 2011). Given that many of Ace’s users are disengaged learners who struggle with traditional education, creating a chatbot with a slightly cheesy, friendly personality was essential to building rapport and encouraging participation. By occasionally inserting lighthearted jokes or brain teasers, Ace creates a low-pressure, fun learning environment, helping students re-engage when they feel overwhelmed. Additionally, humor acts as a social equaliser, making interactions feel less like an authoritative exchange and more like a conversation with a supportive mentor. This was especially important for learners who find strict educational settings intimidating or frustrating. Beyond engagement, riddles and brain teasers also serve an educational purpose, stimulating critical thinking, problem-solving, and lateral reasoning skills.

References

Arunkumar, P. (2025). Scenario-Based Learning: Enhancing Education Through Real-World Context. eLearningDOC. https://elearningdoc.com/scenario-based-learning/

Banas, J. A., Dunbar, N., Rodriguez, D., & Liu, S. J. (2011). A review of humor in educational settings: Four decades of research. Communication Education, 60(1), 115-144. https://doi.org/10.1080/03634523.2010.496867

Colby, K. M. (2022). Artificial Intelligence in Education: The Role of Conversational Agents. Educational Technology & Society, 25(3), 45-56.

Deci, E. L., & Ryan, R. M. (1985). Intrinsic motivation and self-determination in human behavior. Springer Science & Business Media.

Durlak, J. A., Weissberg, R. P., Dymnicki, A. B., Taylor, R. D., & Schellinger, K. B. (2011). The impact of enhancing students’ social and emotional learning: A meta-analysis of school-based universal interventions. Child Development, 82(1), 405-432. https://doi.org/10.1111/j.1467-8624.2010.01564.x

EDUCAUSE. (2023). AI and Machine Learning in Higher Education. EDUCAUSE Learning Initiative. Retrieved from https://www.educause.edu/

Gee, J. P. (2003). What video games have to teach us about learning and literacy. Palgrave Macmillan.

Luckin, R., Holmes, W., Griffiths, M., & Forcier, L. B. (2022). Artificial Intelligence and the Future of Learning. Cambridge University Press. Retrieved from https://www.cambridge.org/elt/blog/2021/07/14/ai-in-education/

Reynolds, K. (2023, May 25). The Value of Flexible Training Options. Training. https://trainingmag.com/the-value-of-flexible-training-options/

Roediger, H. L., & Butler, A. C. (2011). The critical role of retrieval practice in long-term retention. Trends in Cognitive Sciences, 15(1), 20-27. https://doi.org/10.1016/j.tics.2010.09.003

Sweller, J. (1988). Cognitive load during problem solving: Effects on learning. Cognitive Science, 12(2), 257-285. https://doi.org/10.1207/s15516709cog1202_4

Yu, R., & Cai, X. (2022, June 30). Imact of Immediacy of Feedback on Continuous Intentions to Use Online Learning From the Student Perspective. Frontiers in Psychology. Volume 13. https://doi.org/10.3389/fpsyg.2022.865680

Vygotsky, L. S. (1978). Mind in Society: The Development of Higher Psychological Processes. Harvard University Press.

Zimmerman, B. J. (2002). Becoming a self-regulated learner: An overview. Theory into Practice, 41(2), 64-70. https://doi.org/10.1207/s15430421tip4102_2