Master Modern Engineering

In the editor below, you'll find a template. Your task is to craft a few-shot prompt that converts informal slang into professional business English. Provide at least 2 examples in the prompt.

Declare a constant 'username' with your name and a let variable 'score' initialized to 0. Log both.

Create an 'age' variable. Write an if/else statement that logs 'Welcome' if age is 18 or older, and 'Access Denied' otherwise.

Create a prompt for an AI that acts as a Front-end UI/UX Critic. Ask it to review a landing page description. Constraints: Tone must be 'constructive but firm', and the output must be a bulleted list of exactly 3 points.

Write a function 'calculateTotal' that takes 'price' and 'quantity' as arguments and returns the total. Log the result for (25, 4).

Craft a Chain-of-Thought prompt for a logical puzzle. The AI must first state the known facts, then the intermediate steps, and finally the conclusion.

Given an array of numbers [2, 4, 6, 8], use .map() to create a new array where each number is squared. Log the result.

We will use the official Google GenAI SDK to interact directly with an LLM from our browser sandbox. **Step 1.** Import `GoogleGenAI` from `https://esm.sh/@google/genai`. **Step 2.** Initialize the client: `const ai = new GoogleGenAI({ apiKey: 'YOUR_GEMINI_API_KEY' })`. **Step 3.** Use `ai.models.generateContent` with the model `gemini-2.5-flash` to ask: "Explain APIs to a 5-year-old in one sentence." **Step 4.** Log `response.text` to the console.

Write a complete System Prompt for an AI bot called 'Tailwind-GPT'. It should only answer questions about Tailwind CSS. If asked about other CSS frameworks, it must politely decline. It should provide code snippets for all answers.

Write a 'for' loop that logs the numbers from 5 down to 1 (countdown).

AI models are stateless; they don't remember previous messages unless you send the entire history every time. Let's use the SDK's built-in chat session manager. **Step 1.** Initialize `GoogleGenAI`. **Step 2.** Create a chat session using `ai.chats.create({ model: 'gemini-2.5-flash' })`. **Step 3.** Send a message: `"I have 5 apples."` and log the response text. **Step 4.** Send another message: `"I ate 2 of them. How many do I have left?"` and log the response.

Create an object 'calculator' with a method 'operate' that takes (a, b, operation). Support 'add' and 'multiply'. Log the result of (10, 5, 'add').

When building applications, you often need the AI to return parsable data (like JSON) instead of raw conversational text. **Step 1.** Ask the AI to generate details for a famous sci-fi movie (Title, Director, Year). **Step 2.** Pass the `config: { responseMimeType: 'application/json' }` option alongside the model and contents. **Step 3.** Log the result. Try doing `JSON.parse(response.text)` to prove it's valid data!

System instructions dictate the fundamental rules of behavior for the AI across an entire session. **Step 1.** Draft a system instruction that tells the AI it is a "Pirate Coding Assistant" who must speak entirely in pirate slang, but still provide accurate JavaScript answers. **Step 2.** Use `ai.models.generateContent` and pass your system instruction into the `config.systemInstruction` field. **Step 3.** Ask it: "How do I declare a variable in JavaScript?" and log the results.