Graded at ingestion, not at answer time
Every passage carries its credibility grade from the moment it enters the corpus. Grading is a property of the source, so it cannot be adjusted to make a particular answer look better supported.
Knowledge
Every number on this page is measured.
Corpus claims are generated from the database rather than written into copy, so what you read here is what the retrieval layer actually holds.
- 16,500+
- sources indexed
- 28,000+
- retrievable passages
- 20+
- therapeutic areas
Evidence before eloquence
A curated knowledge base built to answer with receipts.
91% of retrievable passages come from authoritative, peer-reviewed and institutional sources. Manufacturer-published material is labelled as commercial wherever it is cited.
16,500+
sources indexed across 20+ therapeutic areas
28,000+ passages are retrievable today. The corpus is refreshed continuously, and stale content is archived rather than served.
Source mix, measured
- Authoritative 35.2%
- Peer-reviewed 31.6%
- Institutional 24.6%
- Government 7.0%
- Commercial 1.3%
- Community 0.4%
Share of 28,000+ retrievable passages as of October 2026. 598 stale, archived or unindexed passages are excluded — they cannot be retrieved, so they are not counted.
How the corpus is governed
Four rules that decide what gets in.
Commercial content is labelled as commercial
Manufacturer-published material is retrievable and labelled as commercial wherever it is cited. It sits at 1.3% of retrievable passages, and every generated answer is checked for promotional superlatives about any brand or manufacturer.
Refreshed continuously, archived when stale
Sources are re-crawled on a schedule matched to how fast each one changes — regulatory labels more often than reference material. Content that goes stale is archived rather than served.
Unretrievable content is not counted
Every figure here counts only what retrieval can return. 598 passages that are stale, archived or missing a search vector are excluded from every number published on this site.
Figures derived 2026-10-19 and regenerated from the corpus on each release. Exact values: 16,903 sources, 28,024 retrievable passages, 24 therapeutic areas. Published claims are rounded down so they remain true between regenerations.
Questions we get asked
Straight answers.
- How are sources graded?
- Every passage carries one of six credibility grades, applied when it enters the corpus. The grade is fixed at ingestion, so it cannot be adjusted to make a particular answer look better supported.
- How current are the corpus figures on this site?
- They are generated from production. A website deploy is refused if a published figure overstates what production holds, or if the snapshot behind it is more than 14 days old.
Ask it something your own content team would struggle with.
The corpus is the product. The quickest way to judge it is to probe the edges of your therapeutic area.