Reads the paper
First it works out what is actually in there
Ten readings that turn a manuscript into structure: the organism, the regions, the design, the techniques, the tests, the findings. Everything after this depends on getting this part right.
Writes about it
Then it puts the paper into words
Titles, summaries for three different audiences, the hypothesis, the figure plan, the skeleton of the argument. The writing you have to do anyway, started from what the paper already says.
Argues with it
Then it pushes back
Eleven analyses that treat the manuscript as a claim to be tested rather than a text to be summarized - the reading it will get from a referee, before it gets it from a referee.
Weave for Word
Write submission-ready manuscripts.
Weave AI works where your manuscript is written. It checks your draft against the target journal's requirements, reviews it the way a referee would, and gives you a readiness score before you submit. Arriving late 2026.
Get early accessSecurity and data
Your manuscript stays yours
Weave AI reads your manuscript to run the analysis you asked for. That is the only thing that happens to it.
Never trained on. Your papers are not training data. Nothing you upload teaches the model anything.
Never sold or shared. Not to advertisers, not to data brokers, not to anyone. Your manuscript is not a product we have for sale.
Never read by us. No one at Weave opens, reviews or samples your manuscript.
Encrypted throughout. In transit and at rest, from the moment a file reaches us.
Yours to take back. Delete a manuscript and it is gone. Take your work back out whenever you want.
Questions about Weave AI
What it is, where it runs, and what it does with your work.
What is Weave AI?
One research AI, built to understand neuroscience first. It reads a manuscript the way someone in the field would - working out what the study did, putting it into words, and then pushing back on it - and it runs underneath every Weave product rather than sitting in one of them.
Is Weave AI a separate product I sign up for?
No. It is the intelligence inside the products, not a product with a release date of its own. You meet it in Stream when it follows the literature, in Horizon while the manuscript is being written, in Atlas when you choose a journal, and in the Word add-in before you submit.
Does it work in fields other than neuroscience?
Not yet. We started with neuroscience because that is where we work, and Weave AI will learn one field at a time from there. If your field needs the same kind of reading, checking and drafting, tell us what it looks like - there is a form on the home page, and we read them.
Do you train on my papers?
No. Your papers are not training data, they are never sold or shared, and no one at Weave opens or reviews them. Manuscripts are encrypted in transit and at rest, and you can delete yours at any time.
Where can I use it today?
Weave Stream is live now, so the analyses that run in it are available now too. Weave Atlas arrives in September 2026, the Word add-in in late 2026, and Weave Horizon in early 2027.
Does it replace peer review?
No, and it is not trying to. What it gives you is the reading your paper would get from a careful referee, early enough that you can still do something about it. Every analysis is a draft for you to judge, argue with and throw out - the decisions stay yours.