Prompting Generative AI

Module 03 // Communication Interface

Prompting Generative AI

Learn how an instruction requests an output, why small wording changes can reshape a response, and when to use zero-shot, one-shot, few-shot, character and structured reasoning prompts.

10% syllabus weightingK2 understanding level05 prompt types
USER PROMPT

Explain cloud computing.

→
GENERATED OUTPUT

Cloud computing provides computing services over a network.

Learning Outcome

The Role of Prompts

3.1

A prompt is the instruction given by a user to a generative AI model. It tells the model what output is being requested. A prompt might ask for an explanation, summary, list, recommendation or creative response. The model uses the prompt as immediate context while its transformer also considers patterns learned from training data and the content generated so far.

ROLE 01 // REQUEST

To Request an Output

The prompt starts the interaction. Without a useful instruction, the model does not know the task, subject or expected form of the response.

  • Task: what the model should do.
  • Topic: what the response should discuss.
  • Direction: details such as audience, tone or format.
  • Output: the generated completion returned to the user.
ROLE 02 // GUIDE

Powering the Transformer

The transformer examines the prompt, connects it with learned patterns from training data, and considers each part of the response as it is generated. The prompt therefore guides predictions about what content should come next.

  • The words in the prompt establish context.
  • The transformer uses that context during generation.
  • Each newly generated element becomes additional context.
  • A different instruction can lead to a different output.
01 // INSTRUCTUser enters a prompt.
02 // INTERPRETModel identifies context and task.
03 // GENERATETransformer predicts the continuation.
04 // RETURNUser receives an output.
PROMPT ENGINEERING

Refining Instructions for a Better Output

Prompt engineering is the art of altering and refining prompts to reach a desired or better-quality output. It is often iterative: the user reviews the response, notices what is missing or unsuitable, and rewrites the instruction with clearer direction.

A broad first prompt

“Explain cybersecurity.”

This requests an explanation but gives little direction about audience, length or focus.

A refined prompt

“Explain cybersecurity to a beginner in three short paragraphs and include one everyday example.”

The refined wording gives the model a clearer target.

Why small changes matter: changing a word, adding context or specifying a form changes the context supplied to the transformer. The model may therefore choose a different continuation and produce a noticeably different response. Prompt engineering improves direction, but it does not guarantee that the output is accurate.
Interactive Prompt Refiner
BEFORE
Explain artificial intelligence.
AFTER // ENGINEERED PROMPT

Explain artificial intelligence to a beginner using three short bullet points.

Learning Outcome

Types of Prompts and Their Uses

3.2

Prompt types differ mainly in the guidance supplied to the model. Zero-shot provides no example, one-shot provides one example, and few-shot provides several. Character prompts define a viewpoint, tone or style. Structured reasoning prompts ask the model to work through a complex problem in stages. Select each type to compare its purpose and construction.

Prompt typeExamples suppliedMain useKey distinction
Zero-shotNoneA direct, basic taskThe model receives an instruction but no demonstration.
One-shotOneShow the expected pattern onceOne example guides the desired form.
Few-shotSeveralMake a pattern clearerMultiple examples provide stronger guidance.
CharacterNot defined by examplesSet tone, style or viewpointUses characteristics such as a character, time period or location.
Structured reasoningMay varyHandle a multi-level problemRequests a staged, organised solution.
Core progression: zero-shot → one-shot → few-shot describes an increasing number of examples. In general, examples make the desired pattern clearer, but the prompt must still contain a clear instruction.
Interactive Practice

Prompt Pattern Builder

LAB

Choose a prompt type, enter a task and generate a model prompt. The lab shows how the same request can be framed with different kinds of guidance.



Generated Pattern
Exam-focused Recap

Remember the Distinctions

RECAP
PROMPT

Instruction

A prompt requests an output and gives the transformer immediate context.

ENGINEERING

Refinement

Prompt engineering alters wording and direction to seek a desired or better output.

SHOTS

Number of Examples

Zero means none, one means one, and few means several examples.

CHARACTER

Tone or Style

Characteristics can be based on a character, period or geographical location.

REASONING

Complex Problems

A structured prompt breaks multi-level reasoning into organised stages.

QUALITY

Guidance, Not Guarantee

Clearer prompts can improve relevance, but generated output must still be checked.

Knowledge Check

Test Your Understanding

20 QUESTIONS
SCORE // 0 / 20
Reference Index

Searchable Glossary

KEY TERMS
EXIN BCS Generative Artificial Intelligence Award // Module 03
Unofficial interactive study aid based on the supplied syllabus content.