Answer the two questions that matter
What is in there — and what should not be?
Most organisations are carrying terabytes of files nobody has looked at in a decade — and cannot answer the two questions that matter: what is in there, and what should not be.
Document Analyser crawls SharePoint, OneDrive and network file shares, reads the contents of your documents, and builds a searchable picture of your data estate. The result is a defensible basis for a migration, a privacy remediation programme, a records-retention exercise, or simply a very large storage bill you would like to make smaller.
Runs on your infrastructure • Fixed-price processing • Full API and dashboards
What It Finds
Content and document type
What each file actually is, regardless of what it is named or where it sits.
Sensitive information
PII, health information, financial data, credentials and keys detected in the body of documents.
Duplicates and near-duplicates
The single fastest route to reclaiming storage and reducing risk surface.
Age, ownership and staleness
What can be archived or defensibly disposed of.
Confidence scoring
Every classification is scored, so you can prioritise review rather than trust blindly.
How It Classifies
A layered engine — no single technique is accurate enough alone
Deterministic rule and pattern matching first, natural-language processing for sensitive-information detection, and an AI language model as the fallback for documents the earlier layers cannot resolve.
The AI layer runs on models hosted in New Zealand — your documents are never sent to a third-party AI service.
The analyser comes to the data; the data does not go anywhere
How It's Delivered
Deployed into your environment
The analyser comes to the data; the data does not go anywhere.
Fixed-price processing licence
Banded by data volume so a large or repeated scan cannot produce a runaway bill.
De-duplication detection licence
Separate licence for organisations focused on storage reclamation.
Web interface and full API
Dashboards for the business, endpoints for your automation.
Size the Problem Before You Fix It
Best for councils, government, health, education and not-for-profits facing Privacy Act obligations, records-retention audits, or a data-sprawl problem nobody has been able to size. Book a consultation to see how Document Analyser can help.