AI Prompting Course

Lesson 1 • The Prompt-Response Relationship

Defines the input-output loop and how context shapes responses. Connects model mechanics to practical prompt construction decisions.

Lesson 2 • Setting Up Your Prompting Environment

Guides learners through selecting and configuring AI interfaces for practice. A functional workspace accelerates hands-on skill development from chapter one.

Lesson 3 • How Large Language Models Work

Covers token prediction, training data, and probability-based output generation. Establishes the mechanical basis that explains why prompt wording changes model behaviour.

Lesson 1 • Constraints and Exclusion Rules

Teaches how to define what the model should avoid, exclude, or limit. Negative constraints are as powerful as positive instructions for shaping output.

Lesson 2 • Output Format Specification

Covers explicit formatting instructions such as lists, tables, length limits, and tone. Structured output specifications reduce post-processing effort significantly.

Lesson 3 • Role and Persona Assignment

Teaches how assigning a role to the model shapes tone, expertise level, and framing. Directly improves response relevance without changing the core instruction.

Lesson 4 • Context and Background Injection

Explains how supplying relevant background steers model reasoning toward accurate outputs. Connects context placement to response quality improvements.

Lesson 1 • Chain-of-Thought Prompting

Introduces step-by-step reasoning elicitation to improve complex task accuracy. Connects reasoning transparency to measurable output quality gains.

Lesson 2 • Few-Shot Prompting with Examples

Teaches how to embed input-output examples to guide model behaviour. Examples calibrate format, tone, and reasoning patterns more reliably than instructions alone.

Lesson 3 • Zero-Shot Prompting

Covers direct task prompts without examples and when they are sufficient. Establishes the baseline technique before introducing more complex methods.

Lesson 1 • Writing and Content Generation

Covers prompts for drafting articles, emails, reports, and marketing copy. Task-specific framing dramatically reduces editing time and improves first-draft quality.

Lesson 2 • Classification and Categorisation

Covers prompts that sort, label, and tag inputs into defined categories. Reliable classification prompts enable automation of repetitive triage workflows.

Lesson 3 • Code Generation and Debugging

Applies prompting techniques to software development tasks including writing and fixing code. Structured code prompts reduce ambiguity and improve executable output quality.

Lesson 4 • Summarisation and Extraction

Teaches prompts that condense, extract, and restructure information from source text. Precision extraction prompts are foundational for research and analysis workflows.

Lesson 1 • Prompt Chaining and Pipelines

Introduces sequential prompt chains where one output feeds the next prompt. Chaining enables complex multi-stage tasks that exceed single-prompt capability.

Lesson 2 • Multi-Turn Conversation Design

Covers structuring dialogue sequences where each turn builds on prior context. Well-designed multi-turn flows enable complex task completion across multiple exchanges.

Lesson 3 • Meta-Prompting Strategies

Covers prompts that instruct the model to generate, critique, or improve other prompts. Meta-prompting accelerates prompt development and surfaces blind spots.

Lesson 4 • System Prompts and Persistent Instructions

Explains how system-level prompts set persistent behaviour across a conversation. Mastering system prompts is essential for deploying consistent AI-powered tools.

Lesson 1 • Defining Output Quality Criteria

Teaches how to specify measurable quality dimensions before testing prompts. Clear criteria make evaluation objective and reproducible across team members.

Lesson 2 • A/B Testing Prompts

Introduces controlled comparison of prompt variants to identify performance differences. Structured A/B testing replaces guesswork with evidence-based prompt selection.

Lesson 3 • Manual Evaluation Methods

Covers rubric-based human review processes for assessing prompt outputs. Manual evaluation builds the judgement skills needed to design automated tests.

Lesson 1 • Prompt Documentation Standards

Covers how to write clear metadata, use cases, and performance notes for each prompt. Good documentation transforms individual prompts into reusable organisational assets.

Lesson 2 • Prompt Versioning and Change Control

Introduces version control practices adapted from software development for prompts. Versioning prevents regression and enables safe experimentation on production prompts.

Lesson 3 • Sharing and Collaborating on Prompts

Covers workflows for team-based prompt review, approval, and distribution. Collaborative practices ensure quality control and knowledge transfer across departments.

Lesson 1 • Privacy and Data Sensitivity

Covers handling of personal, confidential, and sensitive data within prompts. Responsible data practices prevent compliance violations and protect stakeholder trust.

Lesson 2 • Governance and Accountability Frameworks

Introduces organisational policies for approving, auditing, and retiring AI prompts. Governance structures ensure accountability and continuous improvement over time.

Lesson 3 • Aligning Prompts with Business Objectives

Connects prompt design decisions to measurable organisational outcomes and KPIs. Strategic alignment ensures AI outputs contribute directly to business value.

Lesson 4 • Prompt Injection and Security Risks

Explains adversarial prompt attacks and how to design defences into prompt architecture. Security-aware prompting is essential for any customer-facing AI deployment.