Why Priors?
There is no open, current record of the evidence for scientific claims within each field.
More than 200 million research papers are now indexed, and millions more are published each year. Each one adds a little to the specific claims a field rests on. But where those claims stand is scattered across experts, papers, conference talks and word of mouth, and it isn't held anywhere you can check.
The IPCC for climate science and Cochrane for medicine pioneered formal evidence synthesis. Their assessments are rigorous and slow: years in the making, covering a fraction of the questions a field asks.
Priors grades every major claim in a field against the same evidence rubric, and keeps it current each quarter and when a major trial reports. Why commercial AI alone cannot do this is on the method page →
Every grade carries its full chain of uncertainty, from the papers behind it to how certain the evidence is. Each field is then sent to independent experts to check, and reviewed fields carry a dated label. Every review is open and free to read, for researchers and for anyone who wants to know where the evidence stands.
FAQ
Because there is nothing you would do inside an app that you can't do by replying. Your email address is your account: it's how release notes and grade changes reach you, how you add or drop topics, and how you ask for a full review. No password to reset, no seat to provision. And you can forward any email to a colleague without them hitting a wall.
Finding papers was never the hard part. Search already does that, and a chatbot will happily summarise one for you. The problem is knowing which papers actually change what the field knows, and by how much. Priors doesn't retrieve or summarise. It tracks the standing claims in your field, weighs each new paper against the existing evidence, and tells you what it changes. It's a measure of where the evidence sits, not a list of links.
The primary literature: randomised trials, cohorts and meta-analyses from the indexed biomedical record. Every claim is backed by a traceable corpus of primary papers, each classified as supporting, neutral or challenging, with the source shown behind every judgment.
A well-known failure of standard language models, and one we built specific guardrails against: every review is anchored to the indexed literature, so each score is built from papers that demonstrably exist and is traceable back to its source. Every DOI is verified against the registry before it ships.
Working researchers and clinicians who need to know where the evidence stands in a field without reading every paper that comes out. You pick your topics; Priors keeps the review current.
Priors applies a systematic, standardised protocol to the key claims in a field, but it is not a replacement for the definitive systematic reviews produced by bodies like Cochrane. Our protocol is built for scale, not depth. Think of it as a reliable first pass that keeps you current and gives you a foundation to build on. Not the final word, and not a substitute for the review you would write yourself. A sceptical first reader. Not peer review, and not medical advice.
46 reviews are live and the catalog is larger; topics publish as their corpus lands. Ask for one and we'll tell you where it sits in the queue, or bring it forward.
Release notes for your fields each quarter, an alert when a pivotal trial moves a claim, and word when your field has been reviewed.
Track your field →Free. No account; unsubscribe by replying.