Classroom exercise cycle: select a task, formulate a baseline prompt, submit it to an LLM, then critically analyse the output before revising instructions¶

Strategy · All strategies
Evidence · no claims cited

Description¶

The paper's core implementable recipe: students select a task relevant to the story they are working on, formulate the baseline prompt from the relevant table, and submit it to an LLM. They must then critically analyse the output by asking which elements are editorially significant, which reflect framing choices embedded in the prompt, which risks (such as hallucination, bias, or oversimplification) are visible and how they would be mitigated before publication, and what further reporting would be needed before the output could inform publication. Prompting is treated as both a practical and reflective activity fostering critical engagement with AI rather than routine use.

Design Implications¶

Context¶

Requirements¶

• An instructor guides students through the evaluative process; the exercise works across any of the tasks in Tables 2, 3, 4, and 5

Constraints¶

Target Learners¶

• journalism students in classroom settings

Target Learning Goals¶

• critical evaluation of AI outputs
• identification and mitigation of task-specific risks
• editorial responsibility and ethical reasoning

Affordances¶

• Llm Journalism Task Taxonomy Four Stages

Related Strategies¶

• Teach prompting as a five-part skill (role, task, audience, constraints, justification) with a structured ask-generate-evaluate cycle
• Implement AI-peer integrated feedback as a standardized two-phase revision cycle with rubric-aligned prompting and instructor monitoring
• Use structured exercises requiring students to compare, critique, and justify against AI-generated code
• Integrate AI feedback as a supportive resource within process-oriented drafting cycles, with explicit guidance on critical evaluation
• Use structured reflection tables, learning journals, prompt variation, adversarial queries, and peer debate to cultivate AI intuition

Examples¶

-

Key Sources¶

• Laurence Dierickx, Fredrik Bjerknes, Andreas L. Opdahl, Carl-Gustav Lindén. (2026). A Taxonomy of LLM-Supported Tasks for Critical AI Literacy in Journalism. Postdigital Science and Education. https://doi.org/10.1007/s42438-026-00690-0