Digital Science has launched Papers AI, an AI-native workspace where researchers write, organize materials, and analyze data without re-explaining their project each time they turn to the assistant for help. Built by the team behind Overleaf, the tool is available now at papers.ai with free and paid options.
The platform is designed specifically for research workflows, combining writing, data analysis, and project management in one place. Rather than working document by document, Papers AI keeps the AI assistant aware of the full project - including drafts, datasets, and references - so researchers don't have to re-upload files or re-state context each time they return to their work.
A single workspace for research projects
Papers AI supports multiple formats including Word, Markdown, Typst, and LaTeX, as well as Jupyter notebooks, CSV files, and Kanban boards. Researchers can run code and work with data in place, then reuse outputs directly as figures and tables in their writing.
The assistant reads the entire project context, not just the document open on screen. This means it can help with data analysis, literature comprehension, and document production without losing track of what the researcher has already done.
Papers AI also ensures nothing enters a project unreviewed. Every AI-suggested change appears as a reviewable edit that the researcher can accept, reject, or adjust before it becomes part of the document. When changes are made in one file, other files update to stay in sync, with a clear record of what changed and why.
Privacy and model flexibility
Data is never used to train AI models. Researchers can run Papers AI completely locally, ensuring no data ever leaves their hardware. The tool also supports connecting external or local AI models in addition to the built-in assistant, giving users control over which model they use.
"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," said Amye Kenall, Chief Product Officer at Digital Science. "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 at 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."
For researchers exploring AI for Science & Research, Papers AI offers a way to keep AI assistance aligned with the full project context. The tool also fits into broader Research workflows by reducing the friction of switching between separate tools for writing, data, and project management.
Why this matters for science and research professionals
Researchers commonly lose time re-explaining context to AI tools that only see a single document or chat session. Papers AI addresses that directly by keeping the assistant aware of the entire project, while ensuring every AI suggestion is reviewable and nothing is changed without the researcher's consent. For professionals managing complex, multi-file research projects, that combination of context-awareness and control could save significant time without sacrificing rigor.
Your membership also unlocks:
