Skip to content
This is NOT an official site of the Government of Canada. Click here for the official AI registry.

AI Assistant for CER XML Code Generation

Employment & Work

What it collects

Operational data
Anonymized data
  • Eligibility requirements documents provided by business analysts, describing rules and logic for the Curam platform. These are internal technical documents and do not contain personal information.
Run by
Employment and Social Development Canada (ESDC)
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 software developers at Employment and Social Development Canada write eligibility-rules XML code for the Curam platform by interpreting requirements documents and answering questions about the codebase through a chat interface. It is an internal developer aid currently in development and does not process personal information. Its primary users are technical staff, not members of the public.

What it collects and what happens to it

Data taken in

Operational data
Anonymized data
  • Eligibility requirements documents provided by business analysts, describing rules and logic for the Curam platform. These are internal technical documents and do not contain personal information.

Processing

Language Models
  • Uses natural language understanding to interpret eligibility requirements documents and respond to developer queries through a chat interface, enabling code generation assistance for the Curam XML environment.

What it does

Creating (Generative AI)
Human decides
  • Generates CER XML code from eligibility requirements documents provided by business analysts. Developers review and decide whether to use the generated code.
Understanding (Semantic AI)
Human decides
  • Provides a context-aware chat interface that understands questions about Curam structure and codebase, returning relevant answers grounded in the platform's architecture and documentation.

Outputs

Generated content
Anonymized data
  • CER XML code generated from eligibility requirements documents, intended for developer review and use in the Curam benefits-delivery platform. No personal information is contained in the output.

Run by

Employment and Social Development Canada (ESDC)
  • The federal department responsible for deploying this AI tool to support internal software development work on the Curam benefits-delivery platform.

Government of Canada AI Register — Curam XML Assistant

Built by

Accenture
  • The technology vendor that developed the Curam XML Assistant for Employment and Social Development Canada.

Government of Canada AI Register — Curam XML Assistant

Kept for

Not stated by the Helpful Places.

Shared with

Not available to me
  • This is an internal developer tool. Members of the public do not have access to the system or its outputs.
Available to the accountable organization
  • Generated code and chat outputs are available to the internal software developers and technical staff at Employment and Social Development Canada who use the tool.

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.

What you can do

Ask about this system

Questions go to the Helpful Places, not the vendor.

Your rights

  • Right to Algorithmic TransparencyThis system is an internal tool used only by Government of Canada software developers. It does not make decisions about members of the public. The existence and general purpose of this system are disclosed through the Government of Canada's AI and Algorithmic Systems Register.

Risks and safeguards

No risks or safeguards have been published for this system yet.