Question

A developer is using Copilot Chat to generate unit tests for several functions in a service class. When asked with a simple instruction like 'write tests for this function,' Copilot produces tests that vary widely in structure, naming conventions, and assertion style across each function. The team has a strict, established test format (Arrange-Act-Assert with specific naming). Which prompting technique will most reliably make Copilot produce tests that consistently match the team's format?

Accepted Answer

Provide a few-shot prompt that includes one or two existing tests written in the team's exact format as examples before asking Copilot to generate the new tests

Answer

Repeat the same zero-shot instruction multiple times until Copilot happens to produce output in the desired format

Answer

Increase the length of the instruction by adding many adjectives describing how good the tests should be

Answer

Ask Copilot to generate the tests and then manually reformat every result to match the team's convention