The Basics of Prompt Engineering

What is Prompt Engineering

Key LLM Concepts

Basic Tips

Traditional vs Reasoning Models

Anatomy of a Prompt

Traditional Model Example

Prompting Reasoning Models

Reasoning Model Example

Introduction

In this course, we teach you how to write effective prompts for Large Language Models (LLMs)—and why prompt engineering is quickly becoming one of the most valuable skills in the AI age. LLMs are powerful tools for reasoning, summarizing, generating, and coding, but their outputs are only as good as the prompts they’re given. Most people waste hours tweaking inputs without understanding why the model behaves the way it does. This course fixes that.

In just under two hours, we cover the foundational mechanics of how LLMs interpret prompts, the anatomy of a well-structured prompt, and how to adapt your approach depending on whether you're using traditional or reasoning models. You'll see real examples where we walk through prompts live, showing both what works and what breaks—and how to fix it.

It’s short, high-signal, and comes with copy-paste prompt templates, annotated examples, and real-world use cases you can apply immediately in your own projects—whether you're writing summaries, generating structured data, or integrating LLMs into your product stack.

It’s taught by Nick, a senior QA engineer and technical project manager who worked on Alexa at Amazon and has spent years translating abstract AI concepts into production-ready workflows. He’s taught thousands of students and consulted with teams deploying LLMs into everything from APIs to internal tools.

You don’t need to know code. You don’t need to understand math. You just need to understand the logic behind the prompt—and that’s what this course is built to teach you.

Whether you’re a developer, product manager, content strategist, or educator, prompt engineering is a core literacy for the new wave of AI tools. And this is the clearest, fastest way to get started.

Get Consistent Results from LLMs

In this course, we'll take you through the basics of prompt engineering - looking at some high level concepts for prompting LLMs, the difference between traditional and reasoning models, and best practices for prompting both to ensure consistant results.

Understand how LLMs interpret inputs by learning tokenization, context windows, and output limits to write more predictable, cost-efficient prompts.

Craft well-structured prompts using a clear framework of task, detail, tone, format, and context to reduce ambiguity and improve output quality.

Select the right model for the job by distinguishing when to use traditional vs. reasoning models based on task complexity and performance tradeoffs.

Improve output consistency and reduce hallucinations by applying structured formatting, clear language, and example-driven prompting techniques.

Watch real-world prompt demos through side-by-side examples that show how different models process the same task and why prompt design matters.

Build AI-native communication skills that are becoming essential across product, engineering, content, and research roles in the AI-driven workplace.

A well-crafted prompt is more than a single sentence—it’s a structured communication that guides a language model toward producing consistent, relevant, and high-quality output. This module breaks down the core components that make up a complete, effective prompt. While there are many frameworks out there, this version focuses on a clear, practical structure that balances precision with flexibility.

At the heart of every prompt is the task—a direct command or request that usually begins with a verb (e.g., summarize, translate, write). It defines the action the model should perform. While LLMs can respond to vague inputs like “hello,” nearly all practical use cases require a task to be clearly defined to produce useful results.

The detail refines the task by adding specificity. This includes particular instructions, constraints, or features you want emphasized in the output. For instance, in a legal summary prompt, the detail might specify which statutes to include; in a poem prompt, it might suggest using metaphors. Detail helps reduce ambiguity and leads to more accurate responses.

The role sets a persona for the model, such as “You are a constitutional lawyer” or “You are a poet and birdwatcher.” This framing can influence the language, knowledge base, and tone the model draws from. While more relevant for traditional models than reasoning models, assigning a role often enhances consistency and realism in outputs, especially for domain-specific tasks.

---
title: Anatomy of a Prompt
privateVideoUrl: https://stream.mux.com/lxdyYQ5dd2r5bnDL4z6a01dqbZO02U02emYkx00OH4y2l02I.m3u8
isPublicLesson: true

---

A well-crafted prompt is more than a single sentence—it’s a structured communication that guides a language model toward producing consistent, relevant, and high-quality output. This module breaks down the core components that make up a complete, effective prompt. While there are many frameworks out there, this version focuses on a clear, practical structure that balances precision with flexibility.

# Task

At the heart of every prompt is the task—a direct command or request that usually begins with a verb (e.g., summarize, translate, write). It defines the action the model should perform. While LLMs can respond to vague inputs like “hello,” nearly all practical use cases require a task to be clearly defined to produce useful results.

# Detail

The detail refines the task by adding specificity. This includes particular instructions, constraints, or features you want emphasized in the output. For instance, in a legal summary prompt, the detail might specify which statutes to include; in a poem prompt, it might suggest using metaphors. Detail helps reduce ambiguity and leads to more accurate responses.

# Role

The role sets a persona for the model, such as “You are a constitutional lawyer” or “You are a poet and birdwatcher.” This framing can influence the language, knowledge base, and tone the model draws from. While more relevant for traditional models than reasoning models, assigning a role often enhances consistency and realism in outputs, especially for domain-specific tasks.

Nick Badot

So now we're going to look at the anatomy of a prompt.

Before I go to this section, I just want to say that I'm going to give you a

list of elements that a thorough prompt would have.

If you look at the anatomy of a prompt, you are probably going to find a lot of

Some of them are going to have three elements, some are going to have five

So this isn't a bible for prompting, this is just one framework of many.

One that I like to use because I think it's the simplest to understand in terms

You'll see that even within this context, it's not super arbitrary, which is

going to be some overlap between these different components of a prompt I'm

So the components themselves are the task, the detail of the task, the role,

which for me only really applies to traditional models, but we'll get to that

Now, task, as you might imagine, is the most basic thing that pretty much

absolutely every prompt needs, even a very simple one.

Now, it is possible to write a prompt without a task.

You can just prompt an alarm by saying hello or something, right?

But in the task, you're generally asking it to do something.

So you're asking it to do an action that contains a verb, usually.

So summarize, spell, calculate, whatever.

So for example, you could be asking, summarize the findings of a court case, XY

Or you could ask something like write a poem by the bluebirds.

Note that there's a verb at the start of those sentences.

There's a verb and there's usually a noun, right?

And 99% of prompts are going to need at least the task.

Now, for very simple prompts, you might be OK with just the task, but usually

just a one-line verb, this noun command is going to be imprecise.

So that's why we want to give a little bit more detail.

Sentence one, the verb the noun, sentence two, give some additional color.

So I'm going to use the same two examples throughout, summarizing a legal case

Here, for example, we could give the detail of, hey, we want you to list the

legal statute to which this really implies and how they're affected.

Or in the use case of the poem, we could say, hey, we want you to use metaphor

likening the bird to a flower, for example.

So this is just getting a little bit more precision and getting a little bit

Now, task and detail together are probably going to cover most of your basic

I remember what I said about not over prompting.

I think if you're trying to one-shot a prompt, you can start with just the task

and that will cover a lot of use cases, and if that doesn't work, then you can

try to get a little bit more technical with it and start using some of these

Now, a role, which I think I already mentioned, is less important than

This is because reasoning models are much more task oriented.

So when I say role, this is, and you might have seen this on some problems,

before you have the list of actions you wanted to carry out, you write like a,

So you could say, if I was generating test data, I would say something like,

you're a senior QA developer who has experienced predicting edge cases and

So to use the two examples I've used already, you could say you're an

experienced constitutional lawyer with known for your rigorous attention to

or you're a bird watcher and a poet that loves striking imagery.

Now, the bit, for example, with striking imagery, that could also have just

It doesn't necessarily need to go into the role.

I'm just pointing that out to show that there is overlap between these concepts

and to reiterate that this isn't a super didactic arbitrary list.

But role can help. I think the concerningly help in terms of the sources that a

model is drawing from, to give your answer and to predict X that comes next.

So I'm just, I'm going to show you one of those two example prompts as we go

You can see I've put hash, role hash, task detail.

I don't actually usually put these in when I'm writing a prompt for a

traditional model, but I'm putting it here just so you guys have the kind of

And you can see I've put task and detail together because for me, they're inext

Now, tone and tone again is something that really synergizes with role.

A lot of people wonder first playing around with chat GPT launch, one of their

They played around with tone a lot, right? You might have seen things like, I

don't know, answer this like a pirate or answer this in an Australian accent or

But aside from just being a fun thing to play around with, it can give a lot

more specificity and consistency to your results, especially if you're asking

it to, for example, use a professional tone or for the poetry example using a

kind of a lively or a lighthearted tone for a fun read.

Stuff like this will get you more consistent results.

Again, it is linked to role and to complex that we're going to see later.

But it's good to know that you can set that tone.

Now, next is format, which for more technical tasks is actually probably one of

the more important elements, especially if you're generating an output that's

then going to be consumed by another system.

Or doing something that's going to be read by someone.

If you're generating a report or a summary, I think specifying a format is very