Write down what good looks like as a set of scored cases before you change anything, then change the prompt or harness and run them again. An eval is a test of behaviour across many runs. It tells you if the change helped, not how it felt.
With agents, a change can feel better and be worse, and any single run can mislead you. If you don't set the bar first, you will end up picking the bar that suits the result you got.
Say it to your agent
“Before we change this prompt, build an eval: 20 past failures and 20 good cases. Decide and write down what score counts as better. Run it 3 times on the current prompt, then on the new one, and show me both.”