AI-Assisted Duplicate Document Detection for ATIP
Inform
What it collects
- Documents stored in AAFC's SharePoint sites, OneDrive, Outlook mailboxes, and staff desktops. The register confirms no personal information is processed.
- Run by
- Agriculture and Agri-Food Canada (AAFC)
- Where
- No fixed location
- Kept
- Not stated by the Helpful Places.
- Shared with
- Accountable organization
What it is for
Document Detective helps Agriculture and Agri-Food Canada's Access to Information and Privacy (ATIP) team find identical or near-identical documents faster by comparing files across SharePoint, OneDrive, Outlook, and staff desktops. The tool is used internally by Government of Canada employees and does not process personal information. Users are informed that AI is in use.
What it collects and what happens to it
Data taken in
- Documents stored in AAFC's SharePoint sites, OneDrive, Outlook mailboxes, and staff desktops. The register confirms no personal information is processed.
Processing
- The tool performs similarity matching — comparing document features to classify pairs as identical or near-identical, built on SSC's automated deduplication platform.
What it does
- The system scores and surfaces identical or near-identical documents for human ATIP officers, who decide how to act on those results during their review process.
Outputs
- Sets of identical or near-identical documents surfaced for ATIP staff review. The output is advisory — human officers make final decisions on how to handle matched documents.
Run by
- AAFC deploys and operates Document Detective to support its Access to Information and Privacy team in finding duplicate and near-duplicate documents across departmental file stores.
Built by
- AAFC's Document Detective is built upon an automated tool originally developed by Shared Services Canada, which supplies the underlying platform.
Kept for
Not stated by the Helpful Places.
Shared with
- Outputs and processing results are available to AAFC's ATIP team and participating Government of Canada employees. The tool is not accessible to members of the public.
Stored
Not stated by the Helpful Places.
How to read the colours
Can it identify you?
- Anonymized data
- Data about people with the link to who is broken. Stripped of identifiers, blurred, aggregated, or noised so this system can’t reasonably tie a record back to an individual.
- Pseudonymous data
- Each person’s data is tied to a token (hash, ID, template) that lets this system recognise the same person across events, but the token itself doesn’t reveal a name. Reidentification is possible with extra information.
- Identifiable data
- The data either contains a direct identifier (name, address, account name, recognisable face or voice, plate number) or carries a token this system uses to look up legal identity during processing.
Who completes the loop?
- Human decides
- This mode suggests; a person decides what to do next. The AI is always advisory — a human is in the loop on every decision. Example: a triage tool ranks cases for a clinician who chooses which to see first.
- Human executes
- This mode decides; a person carries out the result. Example: an optimizer plans the day’s trash-collection routes, and drivers run them.
- Autonomous
- This mode decides and acts on its own. No person reviews each decision or carries out the resulting action.
Definitions from the DTPR standard. Amber is about your data, violet about who decides. The fuller the shape and the deeper the colour, the more identifying the data or the less a person is involved.
- AI registerGovernment of Canada AI Register — Document Detective (2526-AAFC-AAC-004)Agriculture and Agri-Food Canada AI Register entry 2526-AAFC-AAC-004, accessed 2026-01-27.
- AI registerGovernment of Canada AI Register — Document Detective
- AI registerGovernment of Canada AI Register — Document Detective
- Register entryPublished by the Helpful Places. Reference d5461931. This disclosure was drafted with AI assistance.Schema: ai@2026-05-06-beta
What you can do
Ask about this system
Questions go to the Helpful Places, not the vendor.
Your rights
- Right to Be Informed of AI UseGovernment of Canada employees using this system are informed that AI is in use, as confirmed in the official AI register. Further detail on exercising rights can be sought through AAFC's ATIP office.
- Right to Algorithmic TransparencyThe system is listed on the Government of Canada's public AI register, providing general information about its purpose and operation. Contact AAFC's ATIP office for further details about how the system works.
Risks and safeguards
No risks or safeguards have been published for this system yet.