Have you had AI write tests for code you just wrote?

A coding assistant can write unit and integration tests in your existing style. You check that the assertions really test the behavior.

How to automate it

How to automate “click through manual regression tests before each release”

Here are 2 ways to spend less time on this, best first. Each comes with steps you can follow today and, for AI fixes, a prompt to copy.

120 min

typically, once a week

60%

of the time can be automated

A small project

to set up

Fix 1 of 2

AIBest fix

Turn your manual regression checklist into automated browser tests with AI

Coding agents and Playwright's code generator can turn written test steps into end-to-end tests that run on every build. Tools like QA Wolf, mabl and testRigor do this as a service.

Typically saves about 50% of the time8 h to set up

1Pick the 10 regression checks that take longest by hand.
2Give the steps to a coding agent with the prompt below, or record them with Playwright codegen.
3Run them in CI on every merge and review failures each morning.
4Keep only the checks that truly need a human eye as manual tests.

Prompt to copy

Write Playwright tests in [TYPESCRIPT / PYTHON] for these manual regression checks. Use the existing test setup in [FOLDER]. Prefer role- and label-based locators over CSS selectors. Each test should be independent and clean up its own data. After writing them, run them against [TEST URL] and fix flaky waits.

Checks:
[PASTE STEP-BY-STEP CHECKLIST]

Tools: Claude Code, OpenAI Codex, Cursor, GitHub Copilot agent mode or Devin Desktop (ex-Windsurf) · Playwright · QA Wolf · mabl · testRigor

Fix 2 of 2

Have AI write the tests, then you check what they actually assert

Coding agents write good first-pass unit and integration tests in your existing style. Your job shifts to checking the cases and assertions are meaningful.

Typically saves about 45% of the time10 min to set up

1Point the agent at the file or function and an existing test file to copy the style from.
2Use the prompt below; ask for edge cases explicitly.
3Run the tests and make sure at least one fails if you break the code on purpose.
4Delete tests that only check mocks or repeat the implementation.

Prompt to copy

Write tests for [FILE OR FUNCTION] using [TEST FRAMEWORK], following the style of [EXISTING TEST FILE]. Cover the main behavior, edge cases ([EMPTY INPUT, LIMITS, ERRORS]), and any bug fixed recently in [AREA]. Prefer real objects over mocks where it is cheap. Run the tests, fix failures in the tests (not in the code), and list any behavior that looks like a bug instead of changing it.

Tools: Claude Code, OpenAI Codex, Cursor, GitHub Copilot agent mode or Devin Desktop (ex-Windsurf)

Quick wins

Have you tried…

Have you had AI write tests for code you just wrote?: A coding assistant can write unit and integration tests in your existing style. You check that the assertions really test the behavior.

Who does this task

Roles in our library that list this as one of their common tasks. Each guide covers the rest of that role’s week.

QA / Test engineer

HourLeak · the 8-minute work audit

How many hours does this cost you?

The free 8-minute check works out where your week goes and gives you your top fixes. The team scan does the same for everyone and adds it up, so you know which leaks to fix first.

Take the free check Scan my team, $49

Answers are anonymous. Leaders only see team totals.