Prepare and test your skills
Prepare and test your skills
Free sample question, answered and explained below. The Generative AI Leader practice bank has 2,191 more like it. Try 10 free: instant score, no account.
A customer operations team is building a generative AI workflow to categorize unstructured customer feedback into specific internal business categories using a strict JSON format.
When testing prompts that only provide direct instructions, the model frequently misclassifies nuanced complaints and outputs plain text instead of valid JSON. To resolve this, the team adds three representative pairs of customer feedback samples along with their desired JSON output classifications directly into the prompt before presenting the new query.
Which prompting technique is the team using to guide the model's output?
Prompt chaining is a technique where a complex task is broken down into a sequence of smaller, dependent steps, where the output of one prompt serves as the input for the subsequent prompt.
One-shot prompting is an in-context learning method where exactly one demonstration example is provided within the prompt to guide the model's response format and behavior.
Few-shot prompting is an in-context learning technique where a small set of demonstration examples (typically two to five input-output pairs) is included within the prompt context. This allows the model to learn patterns, understand task nuance, and replicate output formatting without requiring parameter updates or model fine-tuning.
When a task involves structured formatting and nuanced domain categorization, providing multiple demonstrations (few-shot prompting) bridges the gap between general instructions and the model's pattern-recognition capabilities.
Zero-shot prompting is a technique where the model is provided only with a task description or instruction without any example input-output demonstrations.
Answer them yourself and get your score the moment you finish. No account needed.
Full access includes
Keep the momentum going with these hand-picked practice scenarios
Last updated