NSK AI
Products · Rudani

Ask once. Read the answer, with its sources attached.

Rudani searches your own documents and writes the answer. Every sentence carries the passage it came from, and anything the documents cannot support, it declines to say.

One question at a time

Watch an answer being assembled.

Pick a question. Rudani retrieves, re-reads, then writes, threading each claim back to the document underneath it.

Query
The breach notification window is now 72 hours from discovery1, and any controller holding more than 50,000 records must name a data protection officer2. Cross-border transfers still clear through the adequacy list published in March3. Retention limits are unchanged, and your standing policy already meets the new bar4.
Sources cited 0
Assembled in
Claims without a source 0
Retrieved
ndpc.gov.ng
Circular 04/2026, breach notification
01
gazette.gov.ng
Federal Gazette No. 118, section 12
02
ndpc.gov.ng
Adequacy list, March 2026
03
internal
Legal memo, 14 April
04
How the answer is made
Four rules
01

Your documents are indexed where they sit.

Rudani reads from the systems you already run. Nothing is copied into an index you do not control.

02

Retrieval is ranked, then re-read.

Candidate passages are read in full before a single word is written, so a ranking mistake does not become an answer mistake.

03

Every sentence is written against a passage.

A claim with no passage behind it does not reach the page. The model is allowed to say that the documents do not answer the question.

04

A citation points at the paragraph, not the file.

Open any number in the answer and you land on the sentence it came from.

It runs where your documents already are.

In your cloud or ours

Self-hosted, in your VPC, or operated by us. Your keys, your logs, your retention policy.

Indexes what you already have

SharePoint, S3, Drive, Confluence, Postgres, and flat scans out of the archive.

Answers in the language asked

The languages your archive is written in, with the passage quoted in its original.

In production
Median answer
1.9s
Largest index in production
41.6M documents
Citations checked against source text
before display
Answers refused for want of evidence
logged, not hidden

The rest of the system

Point it at your own archive.

We index a sample of your documents and hand you the questions it can already answer.