A zoo-sign intern keeps getting unusable plaque drafts until they add a role, a length constraint, and an example of the desired format. They do not change any model weights. Which craft is this?
Select an answer to reveal the explanation.
Short Explanation
Think of rewriting the ask until the plaque looks right: role, length, example. That is prompt engineering, not a weight-changing fine-tune. Cluster counts and learning rates belong to a different shop.
Full Explanation
Prompt engineering is the craft of designing the request, including role, constraints, and examples. The intern did not train weights, so this is not fine-tuning. Cluster count belongs to classical unsupervised models, not plaque wording. Learning-rate search is a training-time hyperparameter task the intern did not run.