AI-Assisted Document Analysis for Program Evaluation
Planning & Decision-making · Research & Development
What it collects
- Technical reports, research papers, financial reports, project management documentation, partner and annual project reports, evaluation reports, audits, and transcripts from interviews or meetings sourced from EDRMS, InfoBank, and SharePoint. The register states no personal information is involved.
- Run by
- Global Affairs Canada (GAC)
- Where
- No fixed location
- Kept
- Not stated by the Helpful Places.
- Shared with
- Accountable organization
What it is for
Document Analyzer helps Global Affairs Canada evaluation teams review large collections of government documents more quickly by using generative AI to extract key findings, trends, risks, and lessons learned. It processes internal reports, financial records, partner submissions, and interview transcripts stored in departmental systems. The tool is used exclusively by Government of Canada employees and does not process personal information. Users are informed that AI is involved in the analysis.
What it collects and what happens to it
Data taken in
- Technical reports, research papers, financial reports, project management documentation, partner and annual project reports, evaluation reports, audits, and transcripts from interviews or meetings sourced from EDRMS, InfoBank, and SharePoint. The register states no personal information is involved.
Processing
- Generative AI language models are used to read, analyze, and synthesize findings across multiple government documents, producing structured summaries for evaluation teams.
- Retrieves and surfaces relevant content from large collections of government documents stored in EDRMS, InfoBank, and SharePoint to support the synthesis and review process.
What it does
- Uses generative AI to synthesize findings across multiple documents, producing summaries of trends, risks, and lessons learned. Human evaluators review and act on the generated outputs.
- Performs structured analysis of document collections to classify, extract, and surface key information such as risks, trends, and lessons learned for human evaluator review.
Outputs
- Structured summaries, syntheses of findings, identified trends, risks, and lessons learned generated from the analysis of program and project documentation. Outputs are advisory and reviewed by human evaluators.
Run by
- Global Affairs Canada is the federal department that deploys and operates Document Analyzer to support its internal evaluation teams in reviewing program and project documentation.
Built by
- The tool was developed internally by the Government of Canada, meaning no external vendor is separately identified. The developing authority and the deploying authority are both the Government of Canada.
Kept for
Not stated by the Helpful Places.
Shared with
- Outputs are available to GC employees within Global Affairs Canada evaluation teams. Access is limited to internal government users.
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 Algorithmic Impact Assessment Registry — Document Analyzer (2526-GAC-AMC-007)Global Affairs Canada / Affaires mondiales Canada, AI Register ID 2526-GAC-AMC-007.
- AI registerGovernment of Canada AI Register — Document Analyzer
- AI registerGovernment of Canada AI Register — Document Analyzer
- Register entryPublished by the Helpful Places. Reference 90fbb4de. 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 UseUsers are informed that AI is involved in the document analysis process. The register confirms that AI use is disclosed to users of the system.
- Right to Algorithmic TransparencyThe Government of Canada has published information about this system in its public AI register, describing how generative AI is used to automate structured document analysis and support evaluation teams.
Risks and safeguards
- Societal & cultural harmAI-generated syntheses of evaluation documents could introduce errors, omissions, or biased framing that influence government program assessments if not carefully reviewed.Safeguard: The system is designed to support rather than replace human evaluators; outputs are reviewed by GC employees before use in formal evaluations. The tool is positioned as an efficiency aid, with human oversight maintained throughout the evaluation process.