Interview metadata often arrives in semi-structured formats, making it difficult to analyse or integrate into standard research workflows. This short prompt-based approach shows how GenAI can transform a JSON file containing interview-related metadata into a clean, structured Excel (.xlsx) file—in seconds, without requiring any programming knowledge. The method enables
University lecturers can improve curriculum planning by using GenAI to create detailed assignment briefs quickly and effectively. This blog introduces a custom prompt that guides GenAI in producing a ready-to-use "AI and Ethics" group presentation brief. It shows how it saves time, incorporates real ethical dilemmas, and suggests
With generative AI tools becoming increasingly common in academic workflows, many researchers are tempted to use them for tasks like journal selection. But can these models really help you decide where to publish? Our quick test in the field of legislative studies suggests: not just yet. We wanted to see
GenAI can be efficiently used as a learning assistant, as demonstrated by this case study. This GenAI prompt assists university students in preparing for exams by targeting a specific topic from their lecture notes. It extracts the relevant section and creates focused revision questions to support active recall and understanding.
Generative AI models have become indispensable tools across industries, but their effectiveness often hinges on the types of input files they can process. Here, we assess the capabilities of leading GenAI interfaces—including Claude, ChatGPT, Gemini, Grok, etc.—examining their support for formats like PDF, JSON, and Python files, and
Natural Language Processing (NLP) allows us to automatically analyse and categorise textual data. With the help of GenAI, even complex classification tasks can now be executed using just a well-designed prompt. In this post, we present a practical example where GenAI classifies financial-related sentences into domain-specific categories, showcasing how effective
Making research accessible to a wider audience is no longer optional – it’s essential to academic life. Whether for public engagement, broader impact, or to ensure that essential findings reach beyond the academic bubble, science communication plays a vital role in connecting scholarship with society. One simple but effective way
Clustering refers to the unsupervised process of grouping similar entities, such as sentences, into categories based on shared characteristics without relying on predefined classes, thus revealing latent patterns in the data. For researchers, GenAI models enable this analysis without the need for programming expertise, offering a powerful means to explore
Recent advances in Generative AI offer researchers new opportunities to assign topic labels to political and legislative texts without manual coding or programming. The Comparative Agendas Project (CAP) provides a structured topic classification system that captures the major areas of public policy. Traditionally, applying these labels required manual annotation or
With the rapid advancement of GenI tools, researchers now have access to innovative ways to improve their manuscripts before journal submission. One such method involves using custom GPT-based reviewers to gain preliminary feedback. To practically evaluate the usefulness of these GPT-driven reviewing tools, we tested the Scientific Paper Reviewer – ChatGPT
Collecting and reviewing relevant literature is often one of the most time-consuming parts of academic research. We tested whether this process could be faster using a single prompt with different generative AI models. To explore this, we prompted each model to return accurate academic articles on ‘legislative backsliding’. The outcome
Writing grammatically correct and stylistically sound academic texts can be a constant challenge for non-native English speakers. Fortunately, with the help of GenAI, it is now possible to review and correct scientific writing quickly and effectively. GenAI can not only detect and correct linguistic errors in seconds but also offer
