Answer at least 13 out of 15 questions correctly to earn your certificate. Questions are randomly selected from a larger bank - each attempt is different.
1.The course recommends changing only one thing at a time when iterating prompts. Why?
2.What temperature should you use for code generation and data extraction?
3.In the ReAct paradigm, what is the correct loop sequence?
4.What does Top-P (Nucleus Sampling) control?
5.In a RAG pipeline, what is the correct order of steps?
6.What is "Prompt Injection" and how do you defend against it?
7.When should you escalate from zero-shot to few-shot?
8.What is an "embedding" in the context of RAG?
9.What problem does "Structured Outputs" solve vs. asking for JSON in the prompt?
10.What is "Constraint Stacking"?
11.What is "Self-Consistency" and how does it build on Chain-of-Thought?
12.What is "Function Calling" (tool use) in LLMs?
13.Why are positive instructions better than negative ones?
14.What is "Data Leakage" in prompt security?
15.What is the "cost-quality ladder" for model selection?