Essentials of prompt engineering
Prompt Engineering Techniques
| Technique | How it works | When to use it |
|---|---|---|
| Zero-shot | The task with no examples | Simple tasks and large, capable models |
| Few-shot (one-shot with a single example) | The task plus a few input and output examples | You need a specific format or style |
| Chain-of-thought (CoT) | Asks the model to reason in intermediate steps, for example "Think step by step" | Multi-step reasoning such as math word problems |
Tips
- Zero-shot works better with larger models and with instruction-tuned models, including those tuned with RLHF.
- Few-shot: pick representative, diverse, clear examples. More examples usually help, but too many add noise.
- CoT can be zero-shot ("think step by step") or few-shot (worked examples that show the reasoning). Combining CoT with few-shot examples is the strongest option for complex reasoning.
Scenario update
Few-shot with the company's report template plus two example reports from earlier product launches.