A prompt template organizes model input and can carry prompting work into supervised fine-tuning (SFT): matching the inference prompt to the training format supports consistency between them. section 4.9.2
Figure 4.7 The graduation decision tree: start with prompting, add RAG when the diagnostic shows a knowledge gap, and graduate to parameter-efficient fine-tuning when prompting plateaus or per-request cost flips the economics.

Use the decision tree to judge when to keep prompting, add retrieval-augmented generation (RAG), or move toward fine-tuning. section 4.9.2


