MaxtDesignAI Studios
All tracks

Prompting Skill track

Prompt Engineering

The moves that take your prompts from vague to executable.

A practical track on writing prompts that produce useful output the first time. Four content modules covering the four moves, examples, structured thinking, and constraint discipline. Plus a capstone quiz. About an hour end to end.

~134 minutes6 modules · 24 lessons

Take the diagnostic first.

Academy progress is tied to your AI IQ participant token. The report that surfaces this track contains a one-click link that brings you back here signed in.

Start the diagnostic

By the end of this track, you will

  • Write prompts the model can act on without guessing.
  • Use examples to encode tone, format, and edge cases.
  • Spot the situations where chain-of-thought actually helps and the ones it does not.
  • Stack constraints the model respects without crossing into the over-stacked spiral.

Syllabus

  1. Module 1

    Before you start

    A short orientation. What this track teaches, what it deliberately leaves out, and how to skip what you already know.

    • LWhat this track is for~4 min

  2. Module 2

    Shape your prompts

    Four moves that take a one-line request from vague to executable. Start here if you mostly write prompts the way you write Google searches.

    • LWhy one-line prompts fail~6 min
    • LA worked example~5 min
    • LFailure modes: when the four moves backfire~6 min
    • LRole priming and persona~5 min
    • DDrill: iterate after a bad first response~6 min

  3. Module 3

    Few-shot and examples

    One good example beats a paragraph of description. When to use examples, how many, the patterns that work, and the three ways examples go wrong.

    • LWhy examples work~5 min
    • LThree mistakes with examples~6 min
    • LExamples for structured outputs~6 min
    • LHow many examples is too many~4 min
    • LNegative examples: showing what not to do~5 min
    • DDrill: find the broken examples~5 min

  4. Module 4

    Chain of thought

    The cheap reliability trick: ask the model to think before answering. Works on logic and analysis, less useful on generation, and partly redundant on reasoning models.

    • LWhen thinking out loud helps~5 min
    • LReasoning models vs prompted chain-of-thought~6 min
    • LStructuring the thinking~5 min
    • LAuditing the reasoning~6 min
    • LWhen chain-of-thought actively hurts~4 min
    • DDrill: trust the reasoning?~5 min

  5. Module 5

    Constraint stacking

    Specific, checkable rules make the difference between an almost-right draft and a ship-ready one. The three tiers, the do-not list, when stacking goes too far, and how to iterate.

    • LMake the constraints checkable~5 min
    • LThe do and do-not pair~4 min
    • LWhen stacking goes too far~6 min
    • LIteration: the half of prompting nobody talks about~6 min
    • DDrill: rescue the over-stacked prompt~5 min

  6. Module 6

    Capstone

    Eight questions across the four modules. Clear 70% to earn the certificate.

    • QFinal quizTake~14 min