Following our previous evaluations of the FutureHouse Platform’s research agents this post turns to Owl, the platform’s tool for precedent and concept detection in academic literature. Owl is intended to help researchers determine whether a given concept has already been defined, thereby streamlining theoretical groundwork and avoiding redundant
Having previously explored the FutureHouse Platform’s agents in tasks such as identifying tailor-made laws and generating a literature review on legislative backsliding, we now directly compare its Falcon agent and OpenAI’s o3. Our aim was to assess their performance on a focused literature search task: compiling a ranked
The FutureHouse Platform, launched in May 2025, is a domain-specific AI environment designed to support various stages of scientific research. It provides researchers with access to four specialised agents — each tailored to a particular task in the knowledge production pipeline: concise information retrieval (Crow), deep literature synthesis (Falcon), precedent detection
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,
Generative AI has made extraordinary strides in recent years, reshaping how researchers write, code, and even analyse data. But a key question remains for academics hoping to automate more of their daily work: Can popular GenAI models like Copilot, Claude 3.7 Sonnet, Gemini 2.0 Flash, GPT-4o, Grok 3
Manus is a general-purpose AI agent designed to carry out multi-step tasks on behalf of users. It promises to understand instructions, break down complex goals, and deliver results—whether that means writing code, automating research workflows, or, in our case, retrieving public data from the web. Touted as the world’
As generative AI tools become increasingly integrated into academic practice, researchers are beginning to explore the use of Custom GPTs—personalised AI variants that operate according to predefined instructions, tone, or tasks. These agents can be configured for specific roles or workflows, such as teaching support, literature exploration, or data
One of the key promises of recent generative AI models is their ability to process not only text and images but also audio and video content. GPT-4.5, with its apparent support for MP3 and MP4 file uploads, seems like an ideal tool for tasks such as transcription — particularly for
In two recent blog posts, we demonstrated how scanned PDFs can be processed using Mistral’s tools—first via a prompt-based approach in Mistral Le Chat, and then through the Mistral OCR API. Both methods effectively extracted readable, structured text from complex documents. But how well do other generative AI
In earlier explorations, we identified the GenAI models that appeared most promising for data visualisation tasks—models that demonstrated strong code generation capabilities, basic support for data wrangling, and compatibility with popular Python libraries such as Matplotlib and Seaborn. In this follow-up case study, we examine a different dimension: rather
Except for Claude 3.7 Sonnet, GPT-4o and GPT-4.5 (which we discussed in a separate post), all other GenAI models we tested encountered issues when asked to generate a simple bar chart from a CSV file. The limitations varied widely—from difficulties in reading the file and missing visualisation
We asked generative AI models to draft a short news-style summary based on a recently published academic article. After generating the initial text, we prompted the models again — this time falsely claiming that a specific expression they had used did not appear in the original publication and had never been
