DEV Community

Cover image for Use Blunt Prompts and Get Shit Done
Lars Moelleken
Lars Moelleken

Posted on

Use Blunt Prompts and Get Shit Done

Do not ask a coding agent for “more tests.”

That is how you get coverage theater.

Ask for pressure:

Increase test coverage by at least 20%.

If you can’t find at least one real regression, your tests are shit anyway.
Enter fullscreen mode Exit fullscreen mode

That prompt works because it has two parts.

First, it gives the agent a measurable floor:

Increase test coverage by at least 20%.
Enter fullscreen mode Exit fullscreen mode

Not “add some tests.”

Not “improve coverage.”

At least 20%.

The number matters because it removes the cheap escape hatch.

Second, it blocks fake success:

If you can’t find at least one real regression...
Enter fullscreen mode Exit fullscreen mode

That changes the job.

The agent is no longer writing tests to satisfy a report.

It is hunting for proof that the code can break.

That is the point.

Coverage alone only says:

This line was executed.

Regression hunting asks:

Did this test prove anything useful?

A weak test can execute code and still protect nothing:

self::assertNotNull($result);
Enter fullscreen mode Exit fullscreen mode

That is not confidence.

That is noise.

A useful test catches broken behavior, exposes a missing edge case, kills a mutant, or forces you to clarify what the code is supposed to do.

  • So push the agent harder.
  • Do not stop at green.
  • Green is the starting line.

The real question is:

What did the new tests actually discover?

If the answer is “nothing,” keep going.

Top comments (0)