Large language models (LLMs) are increasingly embedded in information access systems, extending, and in cases such as ChatGPT, replacing the traditional “10 blue links” paradigm. These systems can enhance knowledge access by summarising large bodies of text or simplifying complex prose, yet they also amplify the risk of overreliance on generated output, potentially eroding users’ critical thinking and information-evaluation skills, an emerging phenomenon sometimes referred to as The ChatGPT Effect. Therefore, this research investigates how scaffolded and personalised cognitive support can help users engage more critically with content in LLM-based information access systems. Drawing on educational psychology and dual-process theories of reasoning, the project examines how nudging and boosting interventions can be designed to (1) adapt to users’ digital literacy and need for cognition, (2) promote meta-cognitive awareness and lateral reading strategies, and (3) preserve autonomy by gradually reducing system support as proficiency increases. The research employs mixed methods, combining user studies with adaptive interface prototyping to evaluate the effects of personalised scaffolds on users’ critical reasoning. The central aim is to introduce critical reasoning processes into LLM-based information access systems through the modelling and evaluation of adaptive scaffolding that initially guides users, analogous to educational instruction, and progressively withdraws assistance as these skills are internalised. By embedding cognitive and pedagogical principles into interactive IR systems, this research advances a new paradigm of human-centred information resilience, shifting the focus from algorithmic detection to the cultivation of critical reasoning skills.