This post shows you how to connect large language models—such as GPT or Claude—directly to Google Docs using Apps Script. With just a few setup steps, you can send selected text to your preferred AI model, receive improved versions, summaries, stylistic rewrites, or even answers to complex questions—
We assessed the ability of Claude 4 Sonnet and GPT-4o to classify brain MRI images as healthy or tumorous for research labelling purposes, using both the chat interface (10 images) and the API (125 images). Claude 4 Sonnet achieved perfect accuracy (10/10) in chat, but its API refused to
Working with real-world text data often means dealing with structures that are not yet analysis-ready. In our case, the dataset included headlines and full article texts stored separately, across two different tables. The only link between them was a shared identifier field: Body ID. Before we could begin any further
Image-based classification is increasingly used across biology, ecology, and agriculture—from identifying animal species to detecting plant diseases. One common use case is the analysis of leaf images to distinguish between healthy and diseased plants. In this post, we compare two approaches to classifying strawberry leaves as either fresh (healthy)
Can we truly distinguish between text produced by artificial intelligence and that written by a human author? As large language models become increasingly sophisticated, the boundary between machine-generated and human-crafted writing is growing ever more elusive. Although a range of detection tools claim to identify AI-generated text with high precision,
Creating visualisations from raw meteorological data no longer requires programming skills. In this post, we demonstrate how researchers can generate a warming stripes diagram – a simple yet powerful visualisation of long-term temperature trends – using only a natural language prompt. We recommend using GPT-4o or GPT-4.5 for this task, as
As data visualisation becomes an increasingly integral part of communicating research and insights, the choice of generative AI models capable of handling both code and chart rendering has never been more important. In this post, we explore which models can be reliably used for visual tasks—such as generating Python-based
In this case study, we demonstrate how generative AI can be used to carry out a full data pre-processing and descriptive analysis workflow on the Nobel Prize dataset. Our objective was to prepare and explore the data in a methodologically sound manner—converting numerical types, handling missing values, verifying completeness,
If your goal is to generate a downloadable .txt file—be it for survey responses, formatted data, or any structured text—not all models can deliver. In this case study, we tested various models to see whether they can create actual .txt files rather than just displaying text or offering
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 models—including Claude 3.7 Sonnet, GPT-4.5, and Qwen2.5-Max—examining their support for formats like PDF, JSON,
As part of testing the synthetic data generation capabilities of GenAI models, we assigned a seemingly simple task to some of the most popular language models: to generate 50 unique customer feedback entries about a smartwatch, including specified fields (name, age, city, feedback, and date of purchase) and a varied
