AWS AI Practitioner Scope

Prompt techniques

Zero-Shot Prompting

• Present a task to the model w/o providing examples or explicit for that specific task
• You fully rely on the model’s general knowledge
• The larger and more capable the FM, the more likely you’ll get good results

Few-shot Prompting

• Provide examples of a task to the model to guide its output
• We provide a “few shots” to the model to perform the task
• If you provide one example only, this is also called “one-shot” or “single-shot”

Chain of Thought (COT)

• Divide the task into a sequence of reasoning steps, leading to more structure and coherence
• Using a sentence like “Think step by step” helps
• Helpful when solving a problem as a human usually requires several steps
• It can be combined with Zero-shot prompting or Few-shot prompting

Retrieval-Augmented Generation (RAG)

• RAG is not a prompt engineering technique but it is often compared to a prompt engineering technique
• Combine the model’s capability with external data sources to generate data sources to generate a more informed and contextually rich response
• The initial prompt is then augmented with external information