General Updated 20 hours ago

AI Literacy & Prompt Engineering Essentials (2026)

Master the core concepts of Generative AI, Large Language Models (LLMs), and advanced Prompt Engineering techniques. This deck covers essential terminology and framework-based prompting (like Chain-of-Thought and Few-Shot) to help you stay competitive in the AI-driven workforce.

11 Views
0 Likes
32 Cards

Cards in this deck

Question #1

What is a "System Prompt"?

Answer

A high-level instruction set that defines the AI's persona, boundaries, and tone before the user interacts with it.

Question #2

Define "Chain-of-Thought" (CoT) Prompting.

Answer

A technique where the AI is asked to "think step-by-step" to improve its reasoning and accuracy in complex tasks.

Question #3

What is "Hallucination" in LLMs?

Answer

A phenomenon where an AI generates confident but factually incorrect or nonsensical information.

Question #4

Few-Shot Prompting vs. Zero-Shot Prompting

Answer

Zero-Shot: Asking the AI to perform a task with no examples. Few-Shot: Providing a few examples of the desired output within the prompt.

Question #5

What does "Temperature" control in AI settings?

Answer

It controls the randomness of the output. Low temperature = focused and predictable; High temperature = creative and diverse.

Question #6

What is an "AI Agent"?

Answer

An autonomous system that uses an LLM to plan tasks, use tools (like searching the web), and achieve a specific goal without constant human input.

Question #7

Define "Token" in the context of LLMs.

Answer

The basic unit of text (chunks of characters or words) that an AI processes. Most models have a "Token Limit" for their memory/context window.

Question #8

What is "RAG" (Retrieval-Augmented Generation)?

Answer

A method that gives an AI access to external, real-time data or specific documents to provide more accurate and up-to-date answers.

Question #9

What is the "Context Window"?

Answer

The total amount of information (tokens) an AI can "remember" and consider at one time during a conversation.

Question #10

Define "Multimodal AI"

Answer

An AI system that can process and generate multiple types of data, such as text, images, audio, and video simultaneously.

Question #11

What is "Self-Consistency" in prompting?

Answer

A technique where you ask the AI to generate multiple different paths to an answer and then pick the most frequent (consistent) result to ensure accuracy.

Question #12

Define "Tree-of-Thoughts" (ToT).

Answer

An advanced reasoning framework where the AI explores multiple branches of a problem simultaneously, evaluating and pruning them like a decision tree.

Question #13

What is "Meta-Prompting"?

Answer

The act of using an AI to write, refine, or optimize a prompt for another AI (or itself) to achieve a better outcome.

Question #14

Define "Prompt Chaining".

Answer

Breaking a complex task into smaller sub-tasks where the output of one prompt becomes the input for the next.

Question #15

What is "ReAct" (Reason + Act)?

Answer

A framework where an AI generates both "reasoning traces" and "action steps," allowing it to use external tools (like a calculator or search engine) while thinking.

Question #16

What is "Grounding" in AI?

Answer

Linking an AI's response to a specific, verifiable source of truth (like a company database) to prevent hallucinations.

Question #17

What is a "Negative Prompt"?

Answer

Specific instructions telling the AI what not to do (e.g., "Do not use jargon" or "Exclude any mention of competitors").

Question #18

Define "Constitutional AI".

Answer

A method of training or prompting AI to follow a specific set of "laws" or ethical principles (a "constitution") to guide its behavior.

Question #19

What is "Prompt Leaking"?

Answer

A security vulnerability where a user cleverly prompts an AI to reveal its underlying system instructions or private developer notes.

Question #20

What is "Delimiters" in prompting?

Answer

Special characters (like ###, """, or ---) used to clearly separate different parts of a prompt, such as instructions from reference text.

Question #21

Define "Stochastic Parrots".

Answer

A critical term used to describe LLMs as systems that repeat patterns of language they’ve seen without a true "understanding" of the meaning.

Question #22

What is "Emergent Ability"?

Answer

A skill or capability that an AI model develops only after reaching a certain size or complexity, which wasn't explicitly programmed into it.

Question #23

Explain "Zero-Shot CoT".

Answer

Triggering an AI's reasoning simply by adding the phrase "Let's think step by step" to a prompt without providing any examples.

Question #24

What is "Parameter Count"?

Answer

A measure of an AI's "brain size" (e.g., 70B, 400B); generally, more parameters allow for more nuanced understanding and knowledge.

Question #25

Define "Adversarial Prompting".

Answer

The practice of testing an AI's limits by trying to trick it into breaking its rules or outputting harmful content (often used for safety testing).

Question #26

What is "RLHF" (Reinforcement Learning from Human Feedback)?

Answer

A training method where humans rank AI responses to help the model learn what humans prefer and find helpful.

Question #27

Define "Context Stuffing".

Answer

The (often poor) practice of cramming too much irrelevant information into a prompt, which can lead to the AI losing track of the main instruction.

Question #28

What is "Fine-Tuning"?

Answer

The process of taking a pre-trained AI and training it further on a smaller, specialized dataset (like medical or legal records).

Question #29

Explain "One-Shot Prompting".

Answer

A prompting style where exactly one example of the desired task is provided to the AI before asking it to perform the task itself.

Question #30

What is "Data Contamination"?

Answer

When the data used to test an AI was actually included in its training set, leading to falsely high performance scores.

Question #31

What is an "LLM Benchmark"?

Answer

Standardized tests (like MMLU or HumanEval) used to compare the performance of different AI models across logic, math, and coding.

Question #32

Define "Recursive Prompting".

Answer

A process where an AI is asked to review its own previous output and improve it in an iterative loop.