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 Packs & Templates Intermediate Bestseller

System Prompt Templates for Developer Tools

Forty production-shaped system prompts for assistants, agents and internal developer tools.

Rated 5.0 out of 5 from 2 reviews 49 students

LM Created by Laura Mbeki

  • Last updated August 2026
  • English
  • 40m of material
  • 5 lessons

What you will learn

6 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.

  • Structure a system prompt as role, scope, refusal policy, output contract and example
  • Write scope boundaries that hold up when a user pushes against them
  • Specify output contracts a parser can rely on, including the failure shape
  • Version system prompts in a repository instead of pasting them into a console
  • Recognise the common system prompt anti-patterns before they reach production
  • Adapt a template to a new tool without losing its safety-relevant lines

Course curriculum

4 modules · 5 lessons · 40m of material

1 lesson running 7m 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.

2 lessons running 14m 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.

1 lesson running 11m 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.

1 lesson running 8m 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 modules · 5 lessons

40m total length

Requirements

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

  • You have called a model API at least once, in any language
  • Basic understanding of JSON and how your application parses it

About this course

A system prompt is the part of an AI feature you cannot see in the screenshot and cannot skip in the build. This pack gives you forty of them, already shaped the way production system prompts end up looking after a few painful weeks: a role line, a hard scope boundary, an explicit refusal policy, an output contract, and a short worked example.

The templates cover the shapes developers keep rebuilding. A support assistant that must never invent a policy. A code explainer bound to one repository. A structured extractor that returns strict JSON. A triage agent that decides between three tools and stops. A migration helper with read-only access. Each one names its variables clearly, marks which lines are safety-relevant, and includes notes on what breaks when you delete them.

You also get the counter-examples: eight system prompts that look reasonable and fail in predictable ways, annotated with why. Reading those is usually faster than discovering the same failures in your own logs.

Delivered as Markdown, a Notion import and a YAML file suitable for checking into a repository. The access link is emailed immediately after checkout and includes every later revision.

Topics covered

Frequently asked questions

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

No. The templates use plain instruction text that works with Claude, ChatGPT and most open models. Provider-specific notes are marked separately where they matter.

Yes. Your purchase includes a personal licence to use and adapt the templates inside products you build. You may not resell the pack itself.

Yes, alongside Markdown and Notion. The YAML file is structured for checking into version control and loading at application start.

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.

5.0

Rated 5.0 out of 5

Course rating · 2 reviews

Rating distribution

  • 5 stars 100%
  • 4 stars 0%
  • 3 stars 0%
  • 2 stars 0%
  • 1 star 0%
  • IS

    Ingvar Solberg

    Platform engineer

    Feb 2026
    Rated 5.0 out of 5

    The annotated failures beat the templates

    Eight prompts that went wrong in production, printed with the transcript and the fix alongside. That section taught me more than the forty working templates did, because it shows you what a failure looks like from the outside before you have diagnosed it.
  • SW

    Sarah Whitmore

    Software engineer

    Dec 2025
    Rated 5.0 out of 5

    Saved a week on our internal assistant

    Our support triage assistant kept inventing ticket statuses that do not exist. One template plus the scope-narrowing advice on adapting it sorted the problem in an afternoon; on my own I would have iterated for days.

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
$3 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.