2026-10-08T21:12:23Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34024047 2026-09-30T02:29:51Z portal_947 item_type_6 month_year_09_2026

Design for Cognitive Friction in Human-AI Interaction: A Student‑Centred AI Scaffold for Cognitive Resilience and Intellectual Agility Nadya Shaznay Patel (10760205) Deliberate cognitive friction Cognitive resilience Intelligence augmentation Dialogic scaffolding Intellectual agility Human-AI interaction <p dir="ltr">This exploratory, design-oriented pilot case study examines Erwin, a student-centred AI scaffold designed to augment students’ thinking in an interdisciplinary design innovation module. Unlike answer-giving chatbots, Erwin adopts a supportive-critic stance: it provides stage-aware, dialogic scaffolding that widens idea spaces and supports criteria-based consolidation through nudges and commitments. The analysis drew on 1,999 student and Erwin turns organised into 171 sessions nested within 78 student logs, alongside post-module qualitative feedback. The study combined reflexive thematic analysis with a full-corpus, non-inferential descriptive analysis of selected interaction-process indicators, including initiative balance, futures probes, completed repair sequences, and system boundary or refusal episodes. A purposive sample of six final artefacts provided illustrative triangulation of interaction patterns and student project trajectories. The analysis identified four practices: disciplined divergence, in which Deliberate Cognitive Friction (DCF) prompts appeared alongside expanded frames without displacing agency; criteria-aware convergence, in which students translated broadened views into clearer problem statements, constraints, and next steps; cognitive resilience visible through repair and persistence sequences; and a supportive-critic experience shaped by answer resistance and meta-reflection. As this was a single-course pilot with no control condition, the descriptive indicators characterise observed interaction processes and contextualise the qualitative interpretation; they are not estimates of causal effects or direct measures of learning outcomes. Across cases, these practices appeared alongside traces of broadened ideation, criteria-guided consolidation, and futures-oriented reasoning in the illustrative artefact sample. The paper contributes situated empirical evidence for studying AI as human augmentation rather than substitution; a transferable design blueprint that operationalises DCF at the prompt policy layer through explainable prompts, resilience guardrails, and instrumentation for scaffolding-oriented LLM systems; and a process-oriented operationalisation of cognitive resilience for Human Computer Interaction in education, understood as interactional evidence of repair, persistence, and flexible reframing rather than as a demonstrated learning effect. The discussion offers implications for designing resilient, trust-preserving human-AI ecosystems that balance augmentation against risks of overreliance and cognitive offloading.</p> 2026-09-30T02:29:51Z Text Journal contribution 10.25447/sit.34024047.v2 https://figshare.com/articles/journal_contribution/Design_for_Cognitive_Friction_in_Human-AI_Interaction_A_Student_Centred_AI_Scaffold_for_Cognitive_Resilience_and_Intellectual_Agility/34024047 In Copyright