Digital Science launches AI-native research workspace Papers AI
Digital Science has launched Papers AI, an AI-native workspace designed to support the research workflow, enabling researchers and students to work across writing, analysis and data management without repeatedly re-establishing context with AI tools.
Developed by the team behind Overleaf, Papers AI is designed to provide a single environment for research projects, combining document creation, data analysis, project management and collaboration.
Rather than limiting AI assistance to individual documents, the platform allows its integrated assistant to work across an entire project, maintaining awareness of drafts, datasets, notebooks and references.
The platform supports multiple research formats, including Microsoft Word, Markdown, Typst and LaTeX documents, alongside Jupyter notebooks, CSV files and Kanban boards. According to Digital Science, this enables researchers to move between writing, coding and project management without switching between separate applications.
A central feature of Papers AI is its context-aware AI assistant, which can access all project materials without requiring users to repeatedly upload documents or explain the background to their work.
AI-generated changes are presented as reviewable edits, allowing researchers to accept, reject or modify suggestions before they are incorporated into a document. Changes made in one file are also reflected across related project files, maintaining consistency throughout the workspace.
Digital Science said the platform has been designed with privacy in mind. Project data is not used to train AI models, and researchers can choose to run Papers AI entirely on their own hardware, ensuring data never leaves their device.
Other features include the ability to execute Jupyter notebook cells alongside written content, integrate outputs directly into figures and tables, and connect external or locally hosted AI models in addition to the platform’s built-in assistant.
The company said feedback from researchers has played a significant role in the development of the platform.
Amye Kenall, Chief Product Officer, Digital Science, said: “Researchers lose enormous amounts of time in the gaps between tools – re-explaining a project to an AI assistant that’s already forgotten it, or ferrying results from one system to another. Papers AI supports the whole research workflow in one place, and it never changes anything quietly: every edit is tracked and every file stays in sync, so researchers stay in control of their own work.”
Juan Castro, Principal AI Scientist, Digital Science, said: “Most AI tools only see the page in front of you. Papers AI’s assistant sees the whole project – the draft, the dataset, the notebook, the references – so it can actually help with the parts of research that take the most time, not just the writing. Trust matters as much as capability here – researchers need to know they’re still the ones making the final call on their own work, and that’s something we’ve built into Papers AI from the start.”
Papers AI is available now at papers.ai, with free and paid options, and sign-up handled directly in the app.