Dayward AIWeChat Mini Program
All courses

5 days · about 17 hours

Prompt Engineering From Scratch in 5 Days

For anyone who has used an AI chat product: in five days, learn to turn a fuzzy requirement into a prompt the model executes reliably, and verify it with a small test set.

Sign in and link WeChat to share one free article per day across both platforms. Unlock more with rewarded videos in the mini program.

Start day one

By the end

A versioned prompt with a ten-case test set that runs on two different model providers

Around a single example task (adding input validation and unit tests to a TODO API), go from the four-element writing pattern all the way to structured output, small-sample evaluation, and cross-model portability

View account and linked status →5 days · about 17 hours

Week 1

From a One-Sentence Requirement to an Evaluable Prompt

01
D1🔒 Locked

What a Prompt Is, and Isn't: How the Model Reads Instructions; the Four Elements of Role / Task / Format / Constraints

First get clear on how the model actually reads what you write, then use four elements — role, task, format, constraints — to turn a fuzzy requirement into a work ticket the model can execute reliably.

02
D2🔒 Locked

Few-Shot, Chain of Thought, Step-by-Step, and Self-Checks; When None of These Work

What problem each of the four most common prompting techniques solves, what it costs, and under what circumstances none of them can save you.

03
D3🔒 Locked

Structured Output: JSON Schema, Templates and Variables, Multilingual Output

Make the model's answer directly consumable by code: constrain the output shape with a schema, turn a prompt into a reusable function with templates and variables, and get the same prompt to reliably output multiple languages.

04
D4🔒 Locked

Iteration and Evaluation: Small Test Sets, A/B Testing, Version Control, Common Anti-Patterns

Turn "this version feels better" into "this version got three more of ten test cases right": build a small test set, run an A/B comparison, version your prompts, and recognize the most common anti-patterns.

05
D5🔒 Locked

Migrating Across Models: Differences Between Claude / GPT / Domestic Chinese Models, Organizing the System Prompt; Where to Go Next — the Claude Course or the Codex Course

Why the same prompt breaks when you switch models, exactly where it breaks, how to organize a system prompt into a portable structure, and whether to study the Claude course or the Codex course next.