Quillionz (Pedro)

At the moment, educators are searching for innovative methods to connect with digital-native students: there is an emerging trend in the use of tools like Google Classroom, Kahoot, Edmodo, Mentimeter, Canva, and even artificial intelligence tools like chatbots or image/video generating AI. However, there is also a growing concern over the fact that “technological innovations need to be transformed from tools of obsession into tools of education” (Wedlock & Growe, 2017, p. 26). In other words, how can we make sure that we as educators are incorporating these tools because they possess educational value and not just because of that trend. In this article we will explore how a digital AI tool like Quillionz can be used in a lesson while tackling its educational benefits and challenges.

Quillionz is an AI-powered content generation platform developed to help teachers create quizzes, discussion questions, and assessments from educational texts. As explained by Braynard (2024), it uses natural language processing (NLP) to analyse input text and automatically generate relevant and well-structured questions, summaries, and keywords. The tool allows educators to paste or upload a text, and within seconds it suggests multiple question types such as multiple choice, recall, and short answer, which can be further edited or adapted according to learners’ needs.

According to Wright (2025), Quillionz represents an efficient way of reducing teachers’ workload while promoting critical reading and comprehension among students. Moreover, it supports Bloom’s taxonomy by allowing teachers to generate questions at different cognitive levels — from remembering and understanding to analysing and evaluating.

In the following tutorial, the use and main features of the tool are explained:

This AI tool seems to offer many benefits to the language classroom. For example, it can support learners in co-creating content by generating draft questions, summaries or prompts that students must refine, evaluate and improve using their own knowledge and critical thinking. This human–AI cooperation aligns with what Jain & Samuel (2025) define as the “co-curation” level in the reconceptualised Bloom’s Taxonomy, where learners and AI co-pilot the creation of meaning while students develop “Critical Understanding” of digital processes. In other words, Quillionz becomes a springboard for learning, not a replacement for it.

Additionally, according to Romrell (2014), the opportunity to use students’ own mobile devices to access AI tools supports learning that is personalized, situated and connected: personalized because students interact with content and feedback tailored to their level and interests; situated because learning is not confined to the classroom; and connected since learners can instantly access information and share their work with peers and the wider community.

However, Quillionz may also introduce significant pedagogical and ethical challenges. Bekiaridis (2024), referring to the DigCompEdu framework, highlights that teachers must empower learners to understand how AI works, including its potential bias, lack of contextual accuracy, and risks to privacy or academic integrity. When using Quillionz, students must therefore critically evaluate AI-generated questions and avoid relying solely on automated outputs.

By way of illustration, we propose a unit of work, and then, a sample lesson to apply these concepts: 

Click here to see the lesson plan

Unit of Work: Raising Environmental Awareness

Age group & language level: 16-year-old, B1-level students, state-run school

Objectives: By the end of the unit, students will be able to:

• Identify key environmental challenges through reading sources

• Create comprehension questions related to environmental topics

• Use Quillionz to generate question sets from environmental texts

• Evaluate and refine AI-generated questions critically

• Lead a class quiz or discussion based on their final question set

• Reflect on how AI can help spread environmental knowledge responsibly

In the following lesson, learners could first read a short text about pollution, climate change or recycling. Once they understand the content, they upload the text into Quillionz, which generates a set of questions. Students then work in groups to edit, simplify, correct or improve those questions to match the B1 level. Finally, they use the revised set to quiz another group, fostering communication and collaborative learning, while also reflecting on the reliability and usefulness of AI-generated materials.

In conclusion, Quillionz is a valuable tool for creating and personalising comprehension tasks in the EFL classroom. It can save preparation time and empower learners to engage in deeper reflection on environmental issues through questioning. However, its use must be accompanied by awareness and critical thinking, ensuring students actively interrogate AI output rather than accepting it as unquestionable truth.

References

Bekiaridis, G. (2024). Supplement to the DigCompEdu Framework. AI Pioneers. https://aipioneers.org/wp-content/uploads/2024/01/WP3_Supplement_to_the_DigCompEDU_English.pdf

Braynard, T. (2024). Quillionz review: AI-powered question generation for teachers. EdTech Insights. https://edtechinsights.org/quillionz-review

Jain, J., & Samuel, M. (2025). Bloom meets Gen AI: Reconceptualising Bloom’s Taxonomy in the era of co-piloted learning. https://doi.org/10.20944/preprints202501.0271.v1

Romrell, D. (2014). The SAMR model as a framework for evaluating mLearning. https://www.researchgate.net/publication/264549561_The_SAMR_Model_as_a_Framework_for_Evaluating_mLearning

Wedlock, B. C., & Growe, R. (2017). The technology-driven student: How to apply Bloom’s Revised Taxonomy to the digital generations. Journal of Education and Social Policy, 4(1), 26–33. https://jespnet.com/journals/Vol_4_No_1_March_2017/4.pdf

Wright, S. (2025). AI tools for reading comprehension: How Quillionz supports teachers. Teaching Tomorrow Quarterly. https://teachingtomorrow.org/quillionz