UAE · ENBook a demo
RetailEngineeringAssistant

Testing Agent

Writes and runs automated tests.

Testing AgentApplication Engineering
Industry
Retail
Department
Engineering
Team
Application Engineering
Kind
Assistant
Approver
Engineering Manager
Code
ENG-03

It writes and runs automated tests across the storefront, app, order management, store tills and the warehouse integration, covering journeys like buy online pick up in store, split shipments, multi-buy promotions and returns to a different store. It reports what failed with the evidence and files a bug for each real failure.

How it works

6 steps, and a person signs off before step 6.

  1. 01Looks it up

    Finds the record the request is about in the CI/CD pipeline: the test suites, recent runs and results for the journeys and systems named..

  2. 02Reads the request

    Works out what is being asked and what a complete answer needs.

  3. 03Checks the facts

    Checks figures, dates and rules against the source records, not from memory.

  4. 04Works it through

    Prepares the draft, match, recommendation or reply, with its sources.

  5. 05Asks a person

    Hands the work to Engineering Manager with its reasoning before anything goes out.

  6. 06Acts

    Once approved, it acts in the CI/CD pipeline: it runs the tests and files a bug for each real failure. and records what was done.

What it works with

Your knowledge, your systems, your people.

Knows

The test strategy: the critical shopper journeys, the test data rules (test cards only, synthetic shoppers), the till test lanes, the environments and the regression packs for peak trading.

Reads from

the CI/CD pipeline: the test suites, recent runs and results for the journeys and systems named.

Acts in

the CI/CD pipeline: it runs the tests and files a bug for each real failure.

Hands back

An object with run_id, passed, failed, flaky, coverage_percent, failures (a list of test, journey, evidence and bug_id) and release_blocked (true or false).

Asks a person when

A release would go out with a critical journey failing or flagged flaky.

ApproverEngineering Manager

Settings

Your limits, set by your managers.

SettingDefaultWhat it controls
Line coverage needed on changed code (%)80Changed code must reach this coverage.
Retries before a test is called flaky2A test passing only after this many retries is flagged flaky.
Use only payment test cardsOnWhen on, tests use only the payment provider's published test cards.
Journeys that must pass to releasesearch, add to basket, checkout, click-and-collect, returns, loyalty redemptionComma-separated.

Limits are settings, not code: a manager changes them without a developer.

Rules it always follows

  • Every journey in search, add to basket, checkout, click-and-collect, returns, loyalty redemption must pass before a release; a failure there blocks it.
  • Changed code must reach 80 percent line coverage.
  • When on is true, use only the payment provider's test cards and synthetic shoppers; never copy real shopper data into a test environment.
  • A test passing only after 2 retries is flagged flaky, not passed.
  • Test promotions on multi-buys, stacked offers and partial returns, and tills on offline mode and receipt reprint.

See the Testing Agent agent on your own work.

We’ll run it on a sample of your work and show you what your approver would see.

Testing Agent · Retail | Basinwright Industries