// Stage 0 · Prep: AI Literacy
Prompting & Using AI Well
Prompting techniques: role, context, examples, step-by-step thinking and structured output.
about 3 hours3 algorithms1 paperslesson text in progress
01Goals
- Write prompts with goal, background, format and constraints
- Use few-shot examples and chain of thought
- Know when to let the AI search the web or read uploaded files
Do these first: What AI, ML, Deep Learning and LLMs Are
02Algorithms to master
Each card has the original paper, prerequisites and resources.
03Must-read papers
04Courses & videos
- Prompt Engineering Guide ↗Official docsMULTI
- github.com ↗CoursesEN
- Lilian Weng：Prompt Engineering ↗ExplainersEN
05Hands-on: project, code & exercises
Free, official or author-published pages. Most run in the browser or on a free Colab GPU.
PROJECT
Turn a repetitive task from your own work into a reusable prompt template, test it on 5 real cases and iterate three versions.
- 1
- 2OpenAI Cookbook ↗Official docs
Run the official recipes for structured output, classification and summarisation.
06Self-test
Answer in your head, then open to check.
What is few-shot prompting?
Putting a few input–output examples in the prompt so the model follows the pattern.
Why does chain of thought help on maths?
The model writes intermediate steps first, so it makes fewer jump-to-the-answer mistakes.
What should you watch for when asking for JSON?
Give explicit fields and an example, and validate the format in code.
On these routes: Everyday Users · Application Developers · Product Managers & Leaders · Domain Scientists