Prompting: When It's Enough

~10 min read

If your task doesn't need a custom knowledge base and doesn't need to change the model's behavior or style, prompt engineering alone is sufficient — the cheapest, fastest option to reach for first.

Prompting: When It's Enough is a Pro topic

Sign in, then upgrade to Pro or Power to unlock this topic and the full AI Engineering curriculum.

Key points

  • Prompt engineering is sufficient when a task needs neither a custom knowledge base nor a change to the model's behavior/style
  • 'Behavior' here means vocabulary, writing style, and structural conventions, not just factual knowledge
  • Fits: general summarization, common-knowledge Q&A, general classification, translation, standard-style code generation
  • Prompting has the lowest infrastructure cost and fastest iteration loop of all 3 approaches
  • Prompting should be the default starting point — reach for RAG or fine-tuning only once you've identified a specific gap it can't close