Module 1: Introduction to AI and Prompting

Before you can write great prompts, you need to understand what you are actually talking to. This module demystifies AI language models and explains why the quality of your input directly determines the quality of your output.

Lesson 1.1 — Introduction to AI and LLMs

Large language models (LLMs) like ChatGPT and Gemini are trained on vast amounts of text. They predict the most likely next word based on everything they have read. They do not think — they pattern-match at an extraordinary scale.

Key insight: An LLM is not searching the internet for your answer. It is generating a response based on statistical patterns in its training data. This is why the way you phrase your request matters enormously.

What LLMs Are Good At

• Summarising and rewriting text
• Generating structured content (emails, reports, lists)
• Translating between formats (e.g., bullet points to paragraphs)
• Explaining concepts in plain language
• Drafting first versions of documents

What LLMs Struggle With

• Real-time information (unless connected to the internet)
• Precise arithmetic and calculations
• Remembering previous conversations (without memory features)
• Tasks that require physical interaction with systems

Lesson 1.2 — The Garbage In, Garbage Out Principle

The single most important concept in prompt engineering is this: the quality of your output is directly proportional to the quality of your input.

Vague prompt → vague answer. Specific, well-structured prompt → specific, useful answer.

Example: Vague vs. Specific

Vague: Write me an email.

Specific: Write a professional follow-up email to a client named Marcus who attended our product demo on Monday. The email should thank him for his time, summarise the three key features we discussed (automated reporting, real-time dashboards, and API integrations), and include a clear call to action asking him to schedule a 30-minute call this week. Tone: warm but professional. Length: under 200 words.

The second prompt gives the AI everything it needs to produce a genuinely useful output. The first prompt produces a generic template that requires significant editing.

The Five Questions to Ask Before Writing Any Prompt

1. Who am I asking the AI to be? (Role)
2. What exactly do I want it to do? (Task)
3. What context does it need to do this well? (Context)
4. What constraints should it follow? (Format, tone, length, audience)
5. What does a good output look like? (Example or benchmark)

These five questions form the foundation of the framework you will learn in Module 2.