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 Intermediate

The Prompt Systems Masterclass: Agents, Evals and Cost Control

The full craft: prompt architecture, agent loops, evaluation harnesses and cost discipline.

18 students

LM Created by Laura Mbeki

  • Last updated August 2026
  • English
  • 13h of material
  • 97 lessons

What you will learn

8 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.

  • Grow a single prompt into a maintainable system without a rewrite
  • Decide when an agent loop earns its cost against a fixed pipeline
  • Route stages to different model sizes and prove the trade on your evals
  • Gate every change behind an eval suite that runs automatically
  • Enforce a cost budget per request instead of discovering it monthly
  • Cache aggressively without serving answers that have gone stale
  • Keep latency acceptable when one request touches several models
  • Hand a prompt system over to a team with documentation they can follow

Course curriculum

8 modules · 97 lessons · 13h of material

12 lessons running 1h 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.

12 lessons running 1h 38m 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.

12 lessons running 1h 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.

12 lessons running 1h 44m 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.

12 lessons running 1h 36m 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.

12 lessons running 1h 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.

12 lessons running 1h 38m 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.

13 lessons running 1h 36m 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.

8 modules · 97 lessons

13h total length

Requirements

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

  • Comfortable writing Python and working with APIs and databases
  • Some prior experience calling a model in an application
  • Willingness to build one project across the whole course

About this course

This is the long course, the one that assembles every separate skill into a single working practice. Thirteen hours, one running project, and a finished system at the end that you could hand to a colleague without an apology.

The project is a research and drafting assistant for a support team. It starts as a single prompt and grows, module by module, into something with a prompt registry, retrieval over an internal corpus, tool access to a ticket system, a bounded agent loop for multi-step questions, structured output feeding a review queue, an eval suite gating every change, guardrails around what it may promise, and a cost budget enforced per request rather than discovered at the end of the month.

Along the way you make the decisions that matter and see the consequences immediately. When does an agent loop beat a fixed pipeline, and what does that cost. Which model size is right for each stage, and how much quality a cheaper model actually loses on your evals. Where caching pays and where it silently serves stale answers. How to keep latency acceptable when a request touches three models.

The closing modules cover the human side: writing the internal documentation, handing over ownership, and running the weekly review of production transcripts that keeps a system honest long after launch.

Topics covered

Frequently asked questions

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

It reuses their vocabulary but not their material. Where a topic has a dedicated course, this one covers the decision and the integration rather than the fundamentals.

Under ten dollars of usage on current pricing if you follow the budget guidance, and a fully cached transcript set is included if you prefer to spend nothing.

Yes. The complete repository at every module boundary is behind your access link, so you can join at any point or compare against your own version.

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

No reviews yet

Nobody has reviewed this course yet, so there is no score to show. Buy it, work through it, and your review could be the one that helps the next developer decide.

Browse the catalog

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
$99 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.