Aim: To compare one-shot and few-shot prompting and observe how demonstrations influence classification consistency.

Prompt / Activity:
ACTIVITY A - ONE-SHOT PROMPT:

Classify the sentiment as Positive, Negative or Neutral. Return only the label.

Example:
Text: The application is very easy to use and saved me a lot of time.
Sentiment: Positive

Now classify:
Text: The update changed the interface, but I have no strong opinion about it.
Sentiment:

ACTIVITY B - FEW-SHOT PROMPT:

Classify the sentiment as Positive, Negative or Neutral. Return only the label.

Examples:
1. Text: The application is very easy to use and saved me a lot of time.
Sentiment: Positive
2. Text: The service crashed twice and I lost my work.
Sentiment: Negative
3. Text: The update changed the interface, but everything still works.
Sentiment: Neutral

Now classify:
Text: The new dashboard looks different, although my workflow remains unchanged.
Sentiment:
