Module · Beginner
Prompt engineering and context
The anatomy of a prompt, the techniques that make models reliable, how tokens and the context window drive cost, how memory works, and the mistakes almost everyone makes first.
Prompts are the interface between people and models. This module makes them precise, measurable and cheap.
- 1 Anatomy of a prompt Understand the roles inside a model request and how an application rebuilds the conversation each time someone sends a message.
- 2 Prompting techniques Choose practical prompting techniques that clarify a task, demonstrate the expected answer and make outputs easier to use.
- 3 Context window, tokens and cost management Understand how tokens share a limited context window and how to manage useful input, answer space and operating cost.
- 4 Memory: short-term and long-term Distinguish conversation history from stored memory and design useful recall with permission, privacy and expiry in mind.
- 5 Common prompt mistakes and fixes Recognise eight recurring prompt problems and replace them with clear goals, consistent evidence, usable outputs and safe escalation.