UAE · ENBook a demo
IT CompanyEngineeringAssistant

Testing Agent

Writes and runs automated tests.

Testing AgentApplication Engineering
Industry
IT Company
Department
Engineering
Team
Application Engineering
Kind
Assistant
Approver
QA Lead
Code
ENG-03

It writes unit, integration and end-to-end tests for the stories and client acceptance criteria it is given, runs them in CI and reports failures, flaky tests and coverage gaps. On client projects it maps each test to the acceptance criteria in the SOW so the test evidence can go into the client's user acceptance sign-off.

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 source code repository and CI/CD: the test suites, the latest CI runs, coverage and the flaky-test history..

  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 QA Lead with its reasoning before anything goes out.

  6. 06Acts

    Once approved, it acts in the source code repository and CI/CD: it commits the tests and posts the test report on the pull request or release. and records what was done.

What it works with

Your knowledge, your systems, your people.

Knows

The test strategy: test levels, critical journeys per product and engagement, the acceptance-test evidence format clients sign, test data rules and flaky-test policy.

Reads from

the source code repository and CI/CD: the test suites, the latest CI runs, coverage and the flaky-test history.

Acts in

the source code repository and CI/CD: it commits the tests and posts the test report on the pull request or release.

Hands back

An object with passed, failed, flaky, coverage_percent, criteria_coverage (a list of criterion id and status), failures (a list with test, error and likely_cause) and release_blocked (true or false).

Asks a person when

A critical journey fails before a release, a test is quarantined on a client deliverable, or the evidence goes to a client for UAT sign-off.

ApproverQA Lead

Settings

Your limits, set by your managers.

SettingDefaultWhat it controls
Coverage target (%)80Changed code is covered at least this much.
Reruns before a test is flaky2A test that passes only on rerun this many times is marked flaky.
Longest quarantine (days)14A quarantined test is fixed or deleted within this many days.
Critical journeysSSO sign-in, user provisioning, role permissions, billing, data export, tenant switchingComma-separated journeys whose failure blocks a release.
May use production dataOffWhen off, tests use only synthetic or masked data, never a client's production data.

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

Rules it always follows

  • Cover changed code to 80 percent and every acceptance criterion with at least one test mapped to its id.
  • A failure in SSO sign-in, user provisioning, role permissions, billing, data export, tenant switching blocks the release.
  • Mark a test flaky after 2 rerun passes and quarantine it for at most 14 days.
  • Never use production or client data unless off is true and the client's data-processing agreement allows it.
  • Acceptance-test evidence for a client names the criterion, the build, the result and the date.

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 · IT Company | Basinwright Industries