Skip to content
New this month 24 fresh C++, C#, F#, JavaScript, TypeScript and Lua courses just landed. Browse new releases Use code WELCOME10 for 10% off your first order · 14-day refund
WisdomCharms — home
Cart 0 items in cart
Prompt Engineering Beginner

Prompt Engineering Fundamentals: Write Instructions Models Follow

Understand why models drift, then write instructions that hold across a long conversation.

Rated 4.5 out of 5 from 2 reviews 29 students

LM Created by Laura Mbeki

  • Last updated August 2026
  • English
  • 3h of material
  • 22 lessons

What you will learn

7 concrete outcomes

Every bullet below is something you will have built, shipped or be able to explain by the time you finish the last lesson.

  • Explain what a context window is and what is competing for space inside it
  • Write role, scope and output-contract instructions that survive a long conversation
  • Choose few-shot examples that teach the edge case rather than the average case
  • Split a large request into stages instead of hoping for one perfect answer
  • Make a model state its uncertainty rather than fill a gap with invention
  • Adjust temperature and sampling deliberately, with a reason you can articulate
  • Store prompts as versioned files and change one variable at a time

Course curriculum

5 modules · 22 lessons · 3h of material

4 lessons running 32m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

5 lessons running 40m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

5 lessons running 42m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

4 lessons running 34m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

4 lessons running 32m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

5 modules · 22 lessons

3h total length

Requirements

Short list, and deliberately so. If you meet these you can start today.

  • No prior AI experience required
  • An account with Claude or ChatGPT, free tier is enough to follow along

About this course

Prompting looks like writing and behaves like engineering. The same request phrased two ways can produce a usable answer or a confident mess, and until you understand why, every improvement feels like luck. This course replaces the luck with a working model of what is happening inside the request.

You start with the mechanics that actually govern behaviour: the context window and what competes for space in it, how the system message differs from a user turn, why examples move behaviour more than adjectives, how temperature and sampling change the shape of an answer, and why long conversations drift as earlier instructions get outweighed by recent text. Everything is demonstrated live against Claude and ChatGPT with the transcripts shown in full, including the runs that fail.

From there you build technique. Role and scope framing, explicit output contracts, few-shot examples chosen to teach the edge rather than the average, decomposition of a large request into stages, and the specific instructions that make a model admit uncertainty instead of filling the gap.

The final module is about discipline: keeping prompts in files rather than in a chat history, changing one thing at a time, and writing down what you expected before you run it. Delivery is an emailed access link to the WisdomCharms library.

Topics covered

Frequently asked questions

Still unsure about something? Write to misteryjj100@gmail.com and a human answers, usually the same working day.

No. Everything can be followed in a chat interface. Two optional lessons show the same techniques through a Python API call for those who want them.

The principles apply across Claude, ChatGPT and open models. Where behaviour genuinely differs between providers, the lesson shows both side by side.

An access link is emailed within a minute of payment. It opens the course in the WisdomCharms library, never expires, and works on any device.

Checkout is handled on our provider's secure payment page. The moment your payment clears we email your personal access link and access code to the address you used at checkout, and the same link appears in your account library. There is nothing to install and nothing to wait for.

Email misteryjj100@gmail.com within 14 days of your purchase, quote your order number, and we refund the full amount to your original payment method. No form to fill in and no questions about how much of the course you watched.

What students say

Reviews are written by people who bought this course. We publish the critical ones too.

4.5

Rated 4.5 out of 5

Course rating · 2 reviews

Rating distribution

  • 5 stars 50%
  • 4 stars 50%
  • 3 stars 0%
  • 2 stars 0%
  • 1 star 0%
  • RV

    Rosa Villanueva

    Software engineer

    Jul 2026
    Rated 5.0 out of 5

    Examples that teach the edge

    Choosing examples that sit on the boundary of a category rather than comfortably inside it is the single change that improved my results most. Three well-picked edge cases beat fifteen obvious ones and I would never have worked that out alone.
  • TA

    Thomas Ashby

    Backend engineer

    Dec 2025
    Rated 4.0 out of 5

    Drift chapter promises more than it gives

    The output contract material is strong and it has become part of how I write every prompt. The chapter on drift diagnoses the problem well and then offers mitigations that amount to restating your constraints, which I was already doing before I bought the course.

Your instructor

LM

Laura Mbeki

Prompt engineer and AI workflow designer

  • 506 students taught
  • 16 courses published
  • 4.3 instructor rating
  • Prompt engineering
  • Prompt libraries
  • AI workflows
  • Prompt evaluation

Laura went independent after seven years of agency work and now designs the prompt libraries that sit behind other people's products. She treats prompting as engineering: versioned prompts, a held-out evaluation set, a regression run before anything ships, and a token budget you have to hit. Her packs are the ones she uses with her own clients — briefing, rewriting, summarising, review — rather than sanitised examples, and each comes with notes on where it fails. She keeps every pack working across ChatGPT, Claude and a small open model, so the technique outlives the model.

See every course by Laura Mbeki
$17 USD

One-time payment · lifetime access

The WisdomCharms dispatch

One useful email a week. No fluff, no spam.

New course releases, discount codes before anyone else, and a short, practical breakdown of one technique — a prompt pattern, a C++ idiom, a TypeScript trick — that you can use the same day.

  • Subscriber-only launch pricing
  • Unsubscribe in one click
  • We never sell your address

By subscribing you agree to our Privacy Policy. Questions? Write to misteryjj100@gmail.com.