AI Chatbot for Canadian Trade and Export Information
Inform · Commerce
What it collects
- The TCS website content, TCS event website, and a curated set of 50 bilingual frequently asked questions serve as the primary knowledge base. This is publicly available operational and informational content, not personal data.
- User messages, triggered topics, session activity, and engagement metrics are captured via Azure Application Insights telemetry logging during chatbot interactions. 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, Vendor
What it is for
This chatbot answers questions about the Trade Commissioner Service (TCS) for Canadian exporters and members of the public visiting the TCS website. It uses generative AI powered by Microsoft Copilot Studio to provide responses grounded in TCS web content, with citations. Users are informed that they are interacting with an AI system. No personal information is collected or processed.
What it collects and what happens to it
Data taken in
- The TCS website content, TCS event website, and a curated set of 50 bilingual frequently asked questions serve as the primary knowledge base. This is publicly available operational and informational content, not personal data.
- User messages, triggered topics, session activity, and engagement metrics are captured via Azure Application Insights telemetry logging during chatbot interactions. The register states no personal information is involved.
Processing
- Microsoft Copilot Studio provides large language model capabilities for generative response generation, grounded in the TCS website content with citation support.
- Semantic matching and trigger phrase refinement for FAQ discovery, along with keyword-based redirection to Other Government Departments, implement retrieval over the curated knowledge base.
What it does
- Generative response generation using Microsoft Copilot Studio, referencing the TCS website with citation support. The chatbot produces new text answers grounded in curated knowledge sources; users decide how to act on the information provided.
- Semantic matching and trigger phrase refinement for FAQ discovery, enabling the system to understand user intent and surface relevant curated answers from 50 bilingual frequently asked questions.
Outputs
- Generative text responses to user queries about Trade Commissioner Service programs and services, produced with citation support referencing the TCS website. Responses are not about any specific individual.
- Telemetry logs capturing triggered topics, session activity, and engagement metrics, used for performance monitoring and service improvement. No personal information is retained in these logs per the register.
Run by
- Global Affairs Canada is the federal department accountable for deploying this chatbot on the Trade Commissioner Service website to assist Canadian exporters and members of the public.
Built by
- Microsoft supplies the generative AI capabilities via Copilot Studio and Azure Application Insights, which power response generation and telemetry logging for this chatbot.
Kept for
Not stated by the Helpful Places.
Shared with
- Telemetry data (user messages, triggered topics, session activity, engagement metrics) captured via Azure Application Insights is available to Global Affairs Canada for service monitoring and improvement purposes.
- Microsoft, as the provider of Copilot Studio and Azure Application Insights, may have access to telemetry and interaction data processed through its platform infrastructure. The extent of vendor data access is not detailed in the register entry.
Stored
- Telemetry and interaction logs are stored on Microsoft Azure infrastructure (Azure Application Insights) as part of the Copilot Studio deployment.
- Duration: Not specified in the register
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 — Trade Commissioner Service website chatbot (DXP)AI Register ID: 2526-GAC-AMC-021, Global Affairs Canada, Status: In production.
- AI registerGovernment of Canada AI Register — 2526-GAC-AMC-021
- AI registerGovernment of Canada AI Register — 2526-GAC-AMC-021
- Register entryPublished by the Helpful Places. Reference 6adf782e. 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 they are interacting with an AI system. The register confirms AI use is disclosed to users.
- Right to Algorithmic TransparencyThe Government of Canada's AI register publicly discloses that this system uses generative AI (Microsoft Copilot Studio), semantic matching, and telemetry logging. Citizens can consult the AI register at open.canada.ca for further details about how the system works.
Risks and safeguards
- Reputational harmGenerative AI may produce inaccurate or misleading information about TCS programs and services, potentially damaging trust in government.Safeguard: Responses are grounded in the TCS website with citation support, enabling users to verify information at source. A multi-environment deployment pipeline (Dev, QA, Staging, Prod) with automated unit testing and performance testing reduces the risk of erroneous outputs reaching production.
- Societal & cultural harmA bilingual public-facing chatbot that fails to serve users equitably in both official languages could undermine the Government of Canada's language obligations and public trust.Safeguard: The system is built on 50 bilingual frequently asked questions and draws on the bilingual TCS website, supporting both English and French users. The Digital Experience Platform project addresses both language communities as part of its design mandate.