In a previous blog post, we focused on input file handling in leading GenAI interfaces, mapping out which formats could be uploaded and processed reliably, and where the main limitations were. This time, we turn to the other side of the equation—output generation—with a concrete test case: producing
In a previous blog, we examined the file handling capabilities of leading GenAI interfaces. That analysis detailed which formats they could process reliably and where they encountered difficulties—particularly with structured data and technical file types. Since then, the landscape has shifted. While downloadable file generation still faces notable constraints,
NotebookLM’s Mind Map function offers researchers a powerful way to quickly grasp the structure and key findings of any uploaded PDF, from academic papers to policy reports. By automatically generating an interactive visual overview, users can explore a study’s objectives, methods, results, and conclusions at a glance. Clicking
We tested the new OpenAI Agent to assess its usefulness in academic research tasks, comparing it directly with Manus.ai and Perplexity’s research mode. Our aim was to evaluate how effectively each tool finds relevant scholarly and policy sources, navigates restricted websites (including captchas and Cloudflare protections), and allows
These tools provide dedicated spaces for creating, refining, and managing content alongside artificial intelligence interactions, facilitating tasks from data visualisation to manuscript drafting. This guide, tailored for researchers, examines their practical applications, operational mechanisms, distinctions, version control capabilities, memory management, and availability in other models. By leveraging these interfaces, researchers
Ensuring a manuscript perfectly adheres to a journal's unique and often complex formatting guidelines is a familiar, laborious task for every researcher. It represents a final, time-consuming hurdle before submission, where minor errors can lead to delays or even desk rejection. But what if this critical checking process
Can artificial intelligence make academic research more accessible to non-specialist audiences—or even to busy researchers on the go? Gemini’s new ‘Audio Overview’ feature provides a novel way to experience scientific papers: through short, conversational audio summaries. Available even in the free version of Gemini 2.5 Flash, this
This post presents a structured application of the Gemini 2.5 Pro language model for the bilingual summarisation of selected Hungarian Constitutional Court decisions. Working exclusively from an official PDF file containing full-text rulings, the model was prompted to generate parallel summaries in Hungarian and UK English, along with a
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—
Integrating Google’s Gemini assistant into Google Docs offers a lightweight yet effective solution for academic and professional editing tasks. Rather than relying on traditional spelling and grammar checkers, users can now issue custom prompts to Gemini—transforming the assistant into a real-time editorial aid capable of producing high-quality revisions
Academic writing increasingly relies on consistent, machine-readable formatting—especially when preparing manuscripts for digital publication, automated parsing, or citation indexing. This post demonstrates how the Mistral Le Chat can accurately convert plain-text bibliographic entries into structured HTML, generating both inline (short-form) citations and full bibliographic records with cross-linked anchors. This
Formatting academic manuscripts in LaTeX can be both laborious and technically demanding—especially when converting raw text into structured, publication-ready documents. This post presents a practical workflow using GPT-4.1 to automate manuscript formatting with remarkable precision. With a single, well-crafted prompt, the model generates clean LaTeX code with proper
