Prompt framework course · 6 chapters · 17 min · certificate
Context Engineering and Structured Prompts
XML tags, LangGPT, the Prompt Canvas, ReAct and agent skills: how to give AI the right information, not just the right words.
What you'll learn
- Curate the right context for AI assistants and agents
- Separate instructions, context, examples, and input with tags
- Build prompts using LangGPT and the Prompt Canvas
- Write system prompts at the right altitude
- Frame agents with goals, tools, and checks
- Apply structured intent to ambiguous recurring tasks
Chapters
6 chapters · 16:35-
2:54
01Start here Members
From prompt to context
This lesson explains what a prompt framework is, then shows how context engineering moves you from writing one prompt to curating everything the model sees, especially for assistants and agents that work over many turns.
-
2:51
02Structure Members
Structure with tags and sections
This lesson teaches you to separate instructions, context, examples and input with consistent tags, and to nest documents with source metadata so the AI reads each part in its proper role.
-
2:44
03Templates Members
LangGPT and the Prompt Canvas
This lesson teaches LangGPT and the Prompt Canvas, two 2024 templates that structure prompts into named sections and one page maps, and shows how they shaped today's skill files and system prompts.
-
2:40
04System prompts Members
The right altitude for system prompts
This lesson teaches how to write system prompts at the right altitude, using canonical examples, a small set of non-overlapping tools, and just in time references instead of pasted content.
-
2:35
05Agents Members
ReAct, tools and agent skills
This lesson teaches the ReAct loop of thought, action and observation, and how to frame agents with goals, tools and checks instead of typing the loop yourself.
-
2:51
06Apply it Members
Structured intent for ambiguous work
This lesson teaches when to apply structured intent, how to build a 5W3H system prompt for a recurring fuzzy task, and how to test it on ten real cases.
Study guide
Context Engineering and Structured Prompts
This course teaches you how to move beyond writing a single clever prompt and start curating the full set of information an AI model sees. You will learn to separate instructions, context, examples, and input with consistent tags, so the model reads each part in its proper role. You will also explore two influential templates from 2024, LangGPT and the Prompt Canvas, and see how they shaped today's skill files and system prompts. The course then shows you how to write system prompts at the right altitude, using canonical examples and just in time references instead of pasted content. Finally, you will learn the ReAct loop of thought, action, and observation, and how to frame agents with goals, tools, and checks. Throughout, you will work with real job examples, such as drafting a launch email or building a recurring report, so you can apply each idea immediately.
In the full study guide
- What is a prompt framework?
- From prompt to context
- Structure with tags and sections
- LangGPT and the Prompt Canvas
- The right altitude for system prompts
- ReAct, tools, and agent skills
- Structured intent for ambiguous work
- 5 frequently asked questions
Jobs this course suits
Our AI checked this course against 500 jobs; these get the most out of it. Each job links to its learning path.