Learn Before
Case Study

Prompting Strategy for a Customer Service Chatbot

A company needs to deploy a customer service chatbot. Their highest priorities are response accuracy and the ability for their non-technical support team to easily understand, audit, and correct the bot's reasoning when it makes a mistake.

  • Team A proposes using human-written, editable text instructions.
  • Team B proposes using automatically optimized numerical vectors that exist only in the model's embedding space. Team B's method achieves 2% higher accuracy, but the vectors are not directly readable by humans.

Which team's approach should the company choose? Justify your decision by evaluating the trade-offs presented by the characteristics of Team B's method.

0

1

Updated 2025-10-03

Contributors are:

Who are from:

Tags

Ch.3 Prompting - Foundations of Large Language Models

Foundations of Large Language Models

Foundations of Large Language Models Course

Computing Sciences

Ch.4 Alignment - Foundations of Large Language Models

Evaluation in Bloom's Taxonomy

Cognitive Psychology

Psychology

Social Science

Empirical Science

Science