Dataset one live
Patents & prior art
Prior-art retrieval over 10.5M+ patents, free to search from your AI assistant. Benchmarked in the open, with the source passage on every result.
0.0M+
US patents in the live index
0
filing languages resolved
0%
examiner citations in top-100 (97,913-query holdout)
Currently processing
EP 4.7M·JP 144k·KR 40k·CN 1.1M translating·48.5M NPL references
Ground truth
Trained on what examiners cited.
Every patent examiner leaves a record: the prior art they cited against each claim. That is millions of labeled claim-to-art pairs, and it is the reason our numbers can be checked rather than asserted. Where the record itself is wrong or incomplete, the people searching it report the fix through the MCP Feedback program.
We structured a decade of it into training and evaluation data, then tuned two retrieval stages on it. The result walks from a claim to the nearest existing art the way the examiner would, across fields and across languages.
How you reach it
One retrieval layer, three ways in.
The retrieval is the same whichever way you reach it. Your assistant calls the MCP server; your platform calls the API; you check the results by hand in the sandbox and the studio.
MCP server
Point your AI assistant or your platform at one endpoint. It plans the retrieval, runs both neural stages, compares claim elements, and returns an answer traced to the source. One call.
Retrieval API
The same two-stage retrieval over REST. Send a claim or a disclosure, get a ranked, scored list with source passages. For teams building their own layer on top.
Sandbox & studio
The sandbox runs a live query and shows the call that produced it. The studio renders the same index as a space you can fly through. Check a result by hand in either before you wire the API into anything.
The call
A claim in. Ranked art, with receipts, out.
No query syntax. Pass the claim text; get back scored matches, examiner-citation lineage, and the exact passage each match rests on.
- locatenearest art, ranked and scored
- compareclaim elements against a reference
- tracethe source passage behind a match
{
"tool": "locate",
"input": {
"claim": "A phone grip with a flexible
accordion member affixed to the rear
housing, expandable between a collapsed
and an extended state."
}
}{
"results": [
{ "id": "US 15,923,629", "score": 0.731,
"examiner_cited_in": 3 },
{ "id": "US 16,777,383", "score": 0.731 },
{ "id": "US 17,021,128", "score": 0.720 }
],
"trace": "specification ¶[0027], verbatim"
}Coverage
Six offices, one index.
The decisive reference is often filed in another jurisdiction and another language. US filings are searchable today; the other five offices are being processed into the same index.
USPTO live
United States
EPO processing
Europe
WIPO processing
PCT / international
JPO processing
Japan
KIPO processing
Korea
CNIPA processing
China
What comes next
Patents are dataset one.
The same pipeline runs on the rest of the legal record. Each dataset is reached the same way, through the same MCP server and API, and corrected the same way, by the people who search it.
Case law & statutes
Strategy
Litigation & dockets
Strategy
Corporate filings
Strategy
Search it from your assistant.
Search is free over MCP on your own key. To build it into a platform over the API, talk to us.