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