AI-Assisted Summarisation and Routing of Ministerial Emails
Inform · Translation & Language Access
What it collects
- Text content of emails submitted to ministers through the departmental correspondence system. The register states no personal information is involved.
- Run by
- Innovation, Science and Economic Development Canada (ISED)
- Where
- No fixed location
- Kept
- Not stated by the Helpful Places.
- Shared with
- Accountable organization
- Your copy
- You cannot see the data it holds about you. What you can do
What it is for
This tool helps staff at Innovation, Science and Economic Development Canada semi-automatically produce bilingual summaries of emails sent to ministers, and routes them to the right internal team. A large language model generates draft summaries in English and French; a human reviewer checks every output before it is used. The system processes correspondence content but does not handle personal information about members of the public.
What it collects and what happens to it
Data taken in
- Text content of emails submitted to ministers through the departmental correspondence system. The register states no personal information is involved.
Processing
- Large language models (LLMs) are used to detect language, summarise email content, and generate bilingual synopses in a consistent format and tone.
- Categorises emails by topic and detects their language to support routing to the appropriate departmental sector.
What it does
- Uses large language models to generate bilingual draft summaries of ministerial emails. Human review is retained at every step before outputs are used.
- Classifies and routes each email to the appropriate internal sector based on detected language and content category.
Outputs
- Bilingual (English and French) draft synopses of ministerial emails, generated in a consistent format and tone for internal staff review before use.
- Routing recommendations directing each email to the appropriate internal sector, based on content classification.
Run by
- The federal department that developed and operates this tool to semi-automate the processing of ministerial correspondence.
Built by
- The tool was developed internally by the Government of Canada, with no external vendor identified in the register entry.
Kept for
Not stated by the Helpful Places.
Shared with
- Outputs (bilingual summaries and routing recommendations) are available to ISED employees who use the web-based interface for correspondence processing.
- Members of the public who sent emails to ministers do not have access to the AI-generated summaries or routing outputs produced about their correspondence.
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 Register — Executive Correspondence Workflow Automation Tool (2526-ISED-ISDE-010)
- AI registerGovernment of Canada AI Register — 2526-ISED-ISDE-010
- AI registerGovernment of Canada AI Register — 2526-ISED-ISDE-010
- Register entryPublished by the Helpful Places. Reference 8cc75923. 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 UseThe register states that AI use is disclosed to users. GC employees using the web-based interface are informed that the tool is AI-enabled. The register does not specify whether members of the public whose correspondence is processed are separately notified of AI involvement.
- Right to Algorithmic TransparencyThis system is listed on the Government of Canada's public AI register, providing transparency about its purpose, data sources, and the fact that human review is retained. Members of the public may consult the register entry at the Government of Canada Open Data portal.
Risks and safeguards
- Psychological harmLLM-generated summaries may misrepresent the intent or tone of correspondence, potentially causing incorrect routing or distortion of a citizen's message.Safeguard: Human review is retained at every step to ensure quality before outputs are acted upon.