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.

Prompt engineering doesn’t always require advanced techniques—many of the most effective prompts come from applying clear, simple communication strategies. This lesson outlines essential practices that apply across all LLMs, regardless of the task or model.

More complex prompts don’t always lead to better results. In fact, zero-shot prompting—where you simply state your request without examples or elaborate instructions—often performs surprisingly well, especially for straightforward tasks. Starting simple lets you test hypotheses quickly and cost-effectively, and gives you a clean baseline to build on if refinement is needed.

Clarity is more important than politeness. LLMs don't need social niceties like “please” or “thank you”—these just add token overhead and can clutter your intent. The model's goal is to interpret commands efficiently, so eliminating unnecessary words and using plain language improves both consistency and cost.

---
title: Basic Tips
privateVideoUrl: https://stream.mux.com/qNn3BuD1vqn01iE016Ewto1oLZJOd45kgSKqhI69b00NsM.m3u8
isPublicLesson: true

---

Prompt engineering doesn’t always require advanced techniques—many of the most effective prompts come from applying clear, simple communication strategies. This lesson outlines essential practices that apply across all LLMs, regardless of the task or model.

# Keep It Simple

More complex prompts don’t always lead to better results. In fact, zero-shot prompting—where you simply state your request without examples or elaborate instructions—often performs surprisingly well, especially for straightforward tasks. Starting simple lets you test hypotheses quickly and cost-effectively, and gives you a clean baseline to build on if refinement is needed.

# Be Clear and Direct

Clarity is more important than politeness. LLMs don't need social niceties like “please” or “thank you”—these just add token overhead and can clutter your intent. The model's goal is to interpret commands efficiently, so eliminating unnecessary words and using plain language improves both consistency and cost.

Nick Badot

Now, I'm going to give some basic kind of overall guidance.

This is also stuff that applies no matter

If you take away anything from this session,

this is probably what you should take away.

You don't always have to make your prompt super complicated.

A lot of the times, a simple zero-shot prompt

And usually a zero-shot prompt is not super expensive.

You can try it, and if that doesn't work,

and use some of the concepts that we're going to go over today

to get a more consistent, more specified result.

Another kind of, I guess, relatively straightforward

thing to keep in mind is to just be very clear and direct.

will add please or thank you to their prompts.

where he estimates the cost of all the additional tokens

from people saying, "Please and thank you to be

somewhere in the millions over the lifetime

I try to avoid any unnecessary extra bits of language.

The model kind of knows that these are generally

not words that need to be taken into the processing step.

words that aren't direct is anything that's ambiguous

or anything that's kind of like a passive tone, right?

We're talking about verbing the noun versus the verb in

is happening to the noun kind of stuff like this.

And another thing you can do is obviously,

if you're using our LEMs, is do test out different models.

Most of them have a free tier that lets you

at least play around with it a little bit.

that ostensibly say that one model is better

But I think honestly, personal preference is often

more important than something being two percentage points

better at answering algebra or something, right?

Unless you have a really specific use case

So yeah, test around, try different problems

on different models, see what works best for you.

Honestly, have some friends that's whereby

They have different strengths and weaknesses.

And people just are going to have different preferences

if they test around a few different models.