Scenario B: constructing, critiquing, and reframing AI-mediated arguments¶

Strategy · All strategies
Evidence · no claims cited

Description¶

A multi-phase writing activity in which students first independently formulate a thesis with reasoning and evidence, then prompt an LLM for counterarguments and critique them using structured criteria focused on logic, bias and credibility, and finally reframe the question from a marginalised perspective (e.g., feminist, Indigenous, postcolonial) and compare how epistemic framing alters argumentative possibilities. Alternating AI-free and AI-mediated phases preserves cognitive ownership while using LLMs for epistemic challenge.

Design Implications¶

Context¶

Requirements¶

• Requires an initial AI-free thesis-construction phase to establish cognitive ownership

Constraints¶

• Offered as a situated example for adaptation, not a fixed template

Target Learners¶

• higher education students

Target Learning Goals¶

• inferential reasoning
• evaluative judgement
• epistemic integrity

Affordances¶

• Llm Critical Thinking Pedagogical Framework

Related Strategies¶

• Scaffolded LLM-collaboration assignment cycle: draft, LLM critique, then rebut or incorporate
• Steelmanning
• Use structured exercises requiring students to compare, critique, and justify against AI-generated code

Examples¶

-

Key Sources¶

• Mireia Vendrell, Samantha-Kaye Johnston. (2026). Scaffolding critical thinking with generative AI: Design principles for integrating large language models in higher education. Computers and Education: Artificial Intelligence. https://doi.org/10.1016/j.caeai.2026.100572