Canada version. Set to Canada: prompts add French-language tests, sales tax by province, A1A 1A1 postal codes and 555-01xx numbers to test data, and keep personal data out under PIPEDA or provincial law. US version

AI Prompts for QA Engineers (Canada)

Prompt templates for Canadian QA teams: test cases for English and French UIs, GST/HST by province, AODA accessibility and Canada-format test data with postal codes.

The interactive tool loads here when JavaScript runs.

About this tool

What is AI Prompts for QA Engineers?

With the region set to Canada, every prompt adds three things a US test plan misses. First, both official languages: if the product offers French, generated test cases cover longer French strings, accented characters, French number and currency formats such as 1 234,56 $, and switching language without losing the user's place. Quebec's Charter of the French language applies to commercial products sold there, so any gap is marked for product or legal review rather than waved through.

Second, sales tax by province. GST, HST, and GST with PST or QST apply differently across provinces, so a checkout test must cover each province the product ships to, using the rate in the product's tax table, never one the model remembers. Third, accessibility: Ontario's Integrated Accessibility Standards Regulation under the AODA requires large organizations' websites to meet WCAG 2.0 level AA, and the prompts use that or the team's higher target.

The synthetic data template produces postal codes in A1A 1A1 format across provinces, phone numbers from the 555-0100 to 555-0199 range reserved for fiction, unit-number address formats and names with French accents.

  • Ten QA templates from test design and bug reports to flaky-test triage and release readiness
  • Framework choice for Playwright, Cypress or Selenium skeletons
  • Boundary value and equivalence class instructions built into test-case prompts
  • Flags emails, phones, card-like numbers and IP addresses in pasted logs
  • Favourites, keyword search and a Markdown library export for your QA wiki
Read the guide: AI for Civil and QA Engineers: Prompts That Respect the Engineer of Record

Updated

How to use AI Prompts for QA Engineers

  1. Name your product and team context, for example B2B billing web app, and pick a region if formats like dates or postcodes matter.
  2. Choose a template: Test cases from a user story, Bug report, Automation skeleton, Exploratory charter, Regression scope and more.
  3. Paste the story, acceptance criteria, notes or diff summary and set options such as the framework or priority scheme.
  4. Run the privacy check on logs or data you pasted, then copy the prompt into your assistant or IDE chat.
  5. Review the output: run the code, prune duplicate cases and confirm expected results with the product owner.

Worked examples

Masking a support ticket before triage

Input

Contact: Olivier Roy, olivier.roy@example.ca, 1-604-555-0175, Postal code V6B 1A1

Output

Contact: [NAME-1], [EMAIL-1], 1-[PHONE-1], Postal code [POSTCODE-1]

The name, email, Vancouver number and postal code are masked. The leading "1-" country code is left, which is harmless.

Checkout tax across provinces

Input

Test cases from a user story, region Canada, story: "As a shopper I see the correct sales tax at checkout for my province"

Output

Partitioned cases for HST provinces, GST-only provinces and territories, GST plus PST provinces and Quebec (GST plus QST), with expected rates left as [FROM TAX TABLE]

Rates change (Nova Scotia's HST changed in 2025), so the test cases point at the product's tax table and the CRA calculator instead of hard-coding numbers.

Background and insight

Boundary value analysis and equivalence partitioning are decades-old test design techniques that models apply well when asked explicitly. If a field accepts 1 to 100 items, the interesting inputs are 0, 1, 2, 99, 100 and 101, plus invalid types. Without that instruction, a model tends to produce happy-path cases. The templates ask for the partition table first, then cases derived from it, so you can see whether a class was missed.

Generated test code is a skeleton, not a suite. A model cannot see your DOM, API contract or fixtures, so it invents selectors and endpoints. The Playwright, Cypress and Selenium template asks for user-facing locators (role, label or text) or test ids rather than CSS chains, explicit TODO comments for anything unknown, and no hard-coded waits, which are a common source of flaky tests.

Test data and logs often contain production customer data. Do not paste real records into a public assistant; under GDPR, data that can still be linked to a person remains personal data even when pseudonymised (Recital 26). The synthetic data template generates fictional records from a schema instead, and the privacy check flags emails, phone numbers, card-like numbers and IP addresses in anything you paste.

Common use cases

  • Sprint test design

    Turn user stories and acceptance criteria into partitioned test cases with boundaries before the build lands.

  • Clear defect reports

    Convert rough notes into reproducible bug reports with severity, environment and evidence sections.

  • Automation starts

    Get a Playwright, Cypress or Selenium skeleton with page objects and TODOs to wire to your app.

  • Release decisions

    Summarise test results, open defects and risks into a release readiness note for the go or no-go meeting.

Tips and limitations

  • Run every critical journey once in French with a long translation; truncated buttons are the most common bilingual defect.
  • Keep a province-by-tax-type matrix in the test plan and update it from the CRA when rates change.
  • Use 555-0100 to 555-0199 for phone fixtures so a mis-sent SMS reaches nobody.

Sources and further reading

Frequently asked questions

Does my app need to work in French?

If you sell to consumers in Quebec, the Charter of the French language sets requirements for French on products, packaging and commercial software. Federal institutions have their own official languages duties. Ask your product or legal team which apply; the prompts flag French gaps for that review.

Which accessibility standard applies in Ontario?

Under the Integrated Accessibility Standards Regulation (O. Reg. 191/11), designated public sector organizations and businesses with 50 or more employees must make public websites and web content meet WCAG 2.0 level AA, with some exceptions. Many teams test to WCAG 2.1 or 2.2 AA to cover it.

How should I test GST, HST and PST?

Partition by tax regime: HST provinces, GST-only provinces and territories, GST plus PST provinces, and Quebec with QST. Take expected rates from the CRA's GST/HST calculator and your provincial sources at the time of testing.

Can I use a real SIN to test a validation rule?

No. Generate SIN-format values that pass or fail the check-digit rule your code implements, label them fictitious, and never use a colleague's or customer's number. The privacy check masks labelled SINs if one slips into a log.

Can I paste production logs into an AI tool?

Not with personal information in them unless your company has approved the tool. PIPEDA or provincial private-sector law applies, and Quebec's Law 25 adds an assessment before personal information leaves the province.

Is there an in-depth guide to AI Prompts for QA Engineers?

Yes. “AI for Civil and QA Engineers: Prompts That Respect the Engineer of Record” covers the background, how it works, common pitfalls and worked examples. Read the full guide.