{"id":197213,"date":"2025-09-30T14:26:09","date_gmt":"2025-09-30T14:26:09","guid":{"rendered":"https:\/\/www.ka.nz\/blog\/\/"},"modified":"2025-10-02T04:52:22","modified_gmt":"2025-10-02T04:52:22","slug":"mastering-prompt-engineering-a-complete-guide-to-ai-communication","status":"publish","type":"post","link":"https:\/\/www.ka.nz\/ar\/blog\/mastering-prompt-engineering-a-complete-guide-to-ai-communication\/","title":{"rendered":"Mastering Prompt Engineering: A Complete Guide to AI Communication"},"content":{"rendered":"
\n\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Welcome to the future of human-AI collaboration!<\/strong> Whether you’re a student, professional, or just curious about AI, this guide will teach you how to communicate effectively with large language models (LLMs) to get the results you need.<\/p>\n

<\/p>\n

Duration:<\/strong> 3-4 hours | Level:<\/strong> Beginner-friendly (no technical background required)<\/p>\n

\n

\u00a0<\/p>\n

<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Table of Contents<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
    \n
  1. Understanding Large Language Models<\/li>\n
  2. AI Memory and Context<\/li>\n
  3. What is RAG?<\/li>\n
  4. Introduction to Prompt Engineering<\/li>\n
  5. The Four Components of a Great Prompt<\/li>\n
  6. Best Practices<\/li>\n
  7. Advanced Techniques<\/li>\n
  8. Code Prompting<\/li>\n
  9. Common Mistakes to Avoid<\/li>\n
  10. Hands-On Exercises<\/li>\n
  11. Real-World Applications<\/li>\n<\/ol>\n
    \n
    \u00a0<\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
    \n\t\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t

    Understanding Large Language Models {#understanding-llms}<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
    \n\t\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t
    \n\t\t\t
    <\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
    \n\t\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t\t\t

    Before we dive into prompt engineering, let’s understand what we’re working with.<\/p>\n

    What is a Large Language Model?<\/strong><\/p>\n

    Think of LLMs as incredibly sophisticated pattern recognition systems. Here’s what they are (and aren’t):<\/p>\n

    What they ARE:<\/strong><\/p>\n

      \n
    • A massive digital library<\/strong> that has processed millions of books, articles, and websites<\/li>\n
    • A pattern recognition system<\/strong> that predicts what word or phrase should come next<\/li>\n
    • A conversation partner<\/strong> designed to be helpful, harmless, and honest<\/li>\n<\/ul>\n

      What they are NOT:<\/strong><\/p>\n

        \n
      • A search engine<\/strong> – They generate responses based on learned patterns, not by looking up facts<\/li>\n
      • A database<\/strong> – They don’t store or retrieve specific information on demand<\/li>\n
      • Infallible<\/strong> – They can make confident-sounding mistakes<\/li>\n<\/ul>\n
        \u00a0<\/div>\n
        \u00a0<\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
        \n\t\t\t\t\t
        \n\t\t\t\t
        \n\t\t\t\t
        \n\t\t\t\t\t

        Video recording of the session<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
        \n\t\t\t\t\t
        \n\t\t\t\t
        \n\t\t\t\t
        \n\t\t\t\t\t\t\t
        \n\t\t\t
        <\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
        \n\t\t\t\t\t
        \n\t\t\t\t
        \n\t\t\t\t
        \n\t\t\t\t\t\t\t
        \n\t\t\t
        <\/div>\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
        \n\t\t\t\t\t
        \n\t\t\t\t
        \n\t\t\t\t
        \n\t\t\t\t\t\t\t
        \n\t\t\t
        <\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
        \n\t\t\t\t\t
        \n\t\t\t\t
        \n\t\t\t\t
        \n\t\t\t\t\t\t\t\t\t

        How LLMs Actually Work<\/strong><\/p>\n

        The process happens in four stages:<\/p>\n

          \n
        1. Training Phase<\/strong>: The AI reads massive amounts of text from diverse sources<\/li>\n
        2. Pattern Learning<\/strong>: It identifies complex relationships between words, phrases, and concepts<\/li>\n
        3. Prediction<\/strong>: When given a prompt, it predicts the most likely response based on patterns<\/li>\n
        4. Generation<\/strong>: It creates text one token (word or word fragment) at a time<\/li>\n<\/ol>\n

          Key Insight:<\/strong> LLMs don’t “understand” like humans do. They’re incredibly sophisticated pattern matchers that predict what should come next based on what they’ve seen before.<\/p>\n

          Important Limitations<\/strong><\/p>\n

          Understanding these limitations will help you craft better prompts:<\/p>\n

            \n
          • Knowledge cutoff dates<\/strong> – Training data stops at a certain point in time<\/li>\n
          • No real-time information<\/strong> – Unless specifically enabled with tools like web search<\/li>\n
          • Hallucinations<\/strong> – Can generate false information with high confidence<\/li>\n
          • No independent verification<\/strong> – Cannot fact-check their own responses<\/li>\n<\/ul>\n
            <\/div>\n
            \u00a0<\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
            \n\t\t\t\t\t
            \n\t\t\t\t
            \n\t\t\t\t
            \n\t\t\t\t\t

            AI Memory and Context {#ai-memory}<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
            \n\t\t\t\t
            \n\t\t\t\t\t\t\t
            \n\t\t\t
            <\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
            \n\t\t\t\t\t
            \n\t\t\t\t
            \n\t\t\t\t
            \n\t\t\t\t\t\t\t\t\t

            Understanding how AI “remembers” information is crucial for effective prompting.<\/p>\n

            <\/p>\n

            Three Types of AI Memory<\/h3>\n

            <\/p>\n

            \n\n\n\n\n\n\n\n
            Memory Type<\/th>\nDescription<\/th>\nHuman Analogy<\/th>\nCharacteristics<\/th>\n<\/tr>\n<\/thead>\n
            Training Memory<\/strong><\/td>\nEverything learned during training<\/td>\nYour education and life experiences<\/td>\nFixed, cannot be changed after training<\/td>\n<\/tr>\n
            Context Window<\/strong><\/td>\nCurrent conversation<\/td>\nShort-term memory<\/td>\nLimited size (4,000-32,000+ words depending on model)<\/td>\n<\/tr>\n
            Session Memory<\/strong><\/td>\nMemory between conversations<\/td>\nMeeting someone new each time<\/td>\nNone – each chat starts fresh<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/figure>\n

            <\/p>\n

            Why this matters:<\/strong> When you start a new conversation, the AI has no memory of previous chats. If you need context from earlier, you must include it in your current prompt.<\/p>\n

            <\/p>\n

            Context Window Example:<\/strong><\/p>\n

            <\/p>\n

            Imagine you’re having a conversation with Claude, and the context window is 8,000 words. Your conversation includes:<\/p>\n

            <\/p>\n

              \n
            • \n
                <\/ul>\n<\/li>\n<\/ul>\n
                  \n
                • Your initial 500-word prompt<\/li>\n
                • Claude’s 600-word response<\/li>\n
                • Your 400-word follow-up<\/li>\n
                • Claude’s 700-word response<\/li>\n<\/ul>\n

                  <\/p>\n

                  <\/p>\n

                  You’ve now used 2,200 words of your context window. The AI can reference anything in this conversation, but once you hit the limit, older parts may be forgotten.<\/p>\n

                  <\/p>\n

                  \n

                  \u00a0<\/h3>\n

                  <\/p>\n

                  <\/figure>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
                  \n\t\t\t\t\t
                  \n\t\t\t\t
                  \n\t\t\t\t
                  \n\t\t\t\t\t

                  What is RAG (Retrieval-Augmented Generation)? {#what-is-rag<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
                  \n\t\t\t\t
                  \n\t\t\t\t\t\t\t
                  \n\t\t\t
                  <\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
                  \n\t\t\t\t
                  \n\t\t\t\t
                  \n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
                  \n\t\t\t\t\t
                  \n\t\t\t\t
                  \n\t\t\t\t
                  \n\t\t\t\t\t\t\t\t\t

                  RAG is a game-changing technique that extends AI capabilities beyond their training data.<\/p>\n

                  <\/p>\n

                  The Problem RAG Solves<\/h3>\n

                  <\/p>\n

                  Standard LLMs face three major limitations:<\/p>\n

                  <\/p>\n

                    \n
                  1. \n
                      <\/ol>\n<\/li>\n<\/ol>\n
                        \n
                      1. They only know what they were trained on<\/li>\n
                      2. Training data has a cutoff date<\/li>\n
                      3. They can’t access specific documents or databases<\/li>\n<\/ol>\n

                        <\/p>\n

                        <\/p>\n

                        How RAG Works<\/h3>\n

                        <\/p>\n

                        RAG follows a three-step process:<\/p>\n

                        <\/p>\n

                          \n
                        1. \n
                            <\/ol>\n<\/li>\n<\/ol>\n
                              \n
                            1. Retrieve<\/strong>: Search external databases, documents, or knowledge bases<\/li>\n
                            2. Augment<\/strong>: Add the retrieved information to your prompt<\/li>\n
                            3. Generate<\/strong>: Create an informed response using both the AI’s knowledge and the retrieved data<\/li>\n<\/ol>\n

                              <\/p>\n

                              <\/p>\n

                              RAG in Action: Before and After<\/h3>\n

                              <\/p>\n

                              Without RAG:<\/strong><\/p>\n

                              <\/p>\n

                              Prompt:<\/strong> “What is our company’s vacation policy?”<\/p>\n

                              <\/p>\n

                              AI Response:<\/strong> “I don’t have access to your specific company’s policies. I’d recommend checking your employee handbook or speaking with your HR department…”<\/p>\n

                              <\/p>\n

                              With RAG:<\/strong><\/p>\n

                              <\/p>\n

                              System behind the scenes:<\/strong> Searches company knowledge base and finds vacation policy document<\/em><\/p>\n

                              <\/p>\n

                              AI Response:<\/strong> “Based on your company’s vacation policy document, full-time employees receive 15 days of paid vacation per year, accruing at a rate of 1.25 days per month. Vacation time can be used after completing 90 days of employment…”<\/p>\n

                              <\/p>\n

                              Real-World RAG Applications<\/h3>\n

                              <\/p>\n

                              Customer Support:<\/strong><\/p>\n

                              <\/p>\n

                              User Question: \"How do I reset my password?\"\n\u2192 RAG searches company help documentation\n\u2192 AI provides exact steps from official documentation\n<\/code><\/pre>\n
                              <\/p>\n
                              Business Analysis:<\/strong><\/p>\n
                              <\/p>\n
                              Executive Question: \"What were our top-selling products last quarter?\"\n\u2192 RAG retrieves Q3 sales reports\n\u2192 AI analyzes data and presents insights\n<\/code><\/pre>\n
                              <\/p>\n
                              Research Assistant:<\/strong><\/p>\n
                              <\/p>\n
                              Academic Question: \"What are recent findings about climate change impact on coral reefs?\"\n\u2192 RAG searches academic databases\n\u2192 AI summarizes recent peer-reviewed papers\n<\/code><\/pre>\n
                              <\/p>\n
                              Creating a Simple RAG Example<\/h3>\n
                              <\/p>\n
                              Let’s create a sample knowledge base file to demonstrate RAG concepts:<\/p>\n
                              <\/p>\n
                              company_policies.txt<\/strong><\/p>\n
                              <\/p>\n
                              ACME Corporation Employee Handbook - Updated January 2025\n\nVACATION POLICY:\n- Full-time employees: 15 days PTO annually\n- Part-time employees: Pro-rated based on hours\n- Accrual begins after 90-day probationary period\n- Maximum rollover: 5 days to next calendar year\n\nREMOTE WORK POLICY:\n- Hybrid schedule: 3 days in office, 2 days remote\n- Fully remote roles: Must be approved by department head\n- Core hours: 10 AM - 3 PM in your local timezone\n- Required equipment: Company-provided laptop and VPN access\n\nEXPENSE REIMBURSEMENT:\n- Submit within 30 days of purchase\n- Requires receipt for expenses over $25\n- Meals: $50 per day limit for business travel\n- Mileage: Current IRS rate ($0.67 per mile as of 2025)\n<\/code><\/pre>\n
                              <\/p>\n
                              Without RAG Prompt:<\/strong> “What’s the meal allowance for business travel at ACME Corporation?”<\/p>\n
                              <\/p>\n
                              With RAG Prompt:<\/strong> “Based on the following company policy document, answer the question: What’s the meal allowance for business travel?<\/p>\n
                              <\/p>\n
                              [Document content inserted here]<\/p>\n
                              <\/p>\n
                              Question: What’s the meal allowance for business travel?”<\/p>\n
                              <\/p>\n
                              The difference? With RAG, the AI has the specific, accurate information needed to answer authoritatively.<\/p>\n
                              \n
                              \u00a0<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
                              \n\t\t\t\t\t
                              \n\t\t\t\t
                              \n\t\t\t\t
                              \n\t\t\t\t\t
                              Introduction to Prompt Engineering {#intro-to-prompting}<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
                              \n\t\t\t\t\t
                              \n\t\t\t\t
                              \n\t\t\t\t
                              \n\t\t\t\t\t\t\t
                              \n\t\t\t
                              <\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
                              \n\t\t\t\t
                              \n\t\t\t\t
                              \n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
                              \n\t\t\t\t\t
                              \n\t\t\t\t
                              \n\t\t\t\t
                              \n\t\t\t\t\t\t\t\t\t
                              What is Prompt Engineering?<\/h3>\n
                              <\/p>\n
                              Definition:<\/strong> The art and science of crafting inputs to get the best possible outputs from AI systems.<\/p>\n
                              <\/p>\n
                              Think of prompt engineering like:<\/p>\n
                              <\/p>\n
                                \n
                              • \n
                                  <\/ul>\n<\/li>\n<\/ul>\n
                                    \n
                                  • Writing clear instructions for a very capable but literal assistant<\/li>\n
                                  • Being a director guiding an actor’s performance<\/li>\n
                                  • Crafting a recipe that others can follow perfectly<\/li>\n<\/ul>\n
                                    <\/p>\n
                                    <\/p>\n
                                    <\/p>\n
                                    <\/p>\n
                                    Why Prompt Engineering Matters<\/h3>\n
                                    <\/p>\n
                                    Better Results<\/strong>: Get more accurate and relevant responses on the first try<\/p>\n
                                    <\/p>\n
                                    Save Time<\/strong>: Reduce the back-and-forth needed to get what you need<\/p>\n
                                    <\/p>\n
                                    Unlock Potential<\/strong>: Access advanced AI capabilities you didn’t know existed<\/p>\n
                                    <\/p>\n
                                    Creative Control<\/strong>: Guide AI to match your style, tone, and specific needs<\/p>\n
                                    <\/p>\n
                                    The Skill That’s In Demand<\/h3>\n
                                    <\/p>\n
                                    As AI becomes integrated into every industry, the ability to effectively communicate with AI systems is becoming as essential as knowing how to use email or search engines. Companies are hiring “Prompt Engineers” with salaries ranging from $175,000 to $335,000 annually.<\/p>\n
                                    \n
                                    \u00a0<\/p>\n
                                    <\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
                                    \n\t\t\t\t\t
                                    \n\t\t\t\t
                                    \n\t\t\t\t
                                    \n\t\t\t\t\t
                                    The Four Components of a Great Prompt {#four-components}<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
                                    \n\t\t\t\t
                                    \n\t\t\t\t\t\t\t
                                    \n\t\t\t
                                    <\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
                                    \n\t\t\t\t\t
                                    \n\t\t\t\t
                                    \n\t\t\t\t
                                    \n\t\t\t\t\t\t\t\t\t
                                    Every effective prompt can be broken down into four key components. Not every prompt needs all four, but understanding them helps you structure your requests.<\/p>\n
                                    <\/p>\n
                                    The Four Components<\/h3>\n
                                    <\/p>\n
                                    [CONTEXT] Who you are and your situation\n    +\n[TASK] What you want the AI to do\n    +\n[FORMAT] How you want the output structured\n    +\n[EXAMPLES] Show what you're looking for\n<\/code><\/pre>\n
                                    <\/p>\n
                                    Let’s explore each component in detail.<\/p>\n
                                    \n
                                    \u00a0<\/p>\n
                                    <\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
                                    \n\t\t\t\t\t
                                    \n\t\t\t\t
                                    \n\t\t\t\t
                                    \n\t\t\t\t\t
                                    1. Context: Setting the Stage<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
                                    \n\t\t\t\t\t
                                    \n\t\t\t\t
                                    \n\t\t\t\t
                                    \n\t\t\t\t\t\t\t
                                    \n\t\t\t
                                    <\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
                                    \n\t\t\t\t\t
                                    \n\t\t\t\t
                                    \n\t\t\t\t
                                    \n\t\t\t\t\t\t\t\t\t
                                    AI needs to understand your perspective to provide appropriate responses. Without context, the AI makes assumptions that might not align with your needs.<\/p>\n
                                    <\/p>\n
                                    Examples of Good Context<\/h3>\n
                                    <\/p>\n
                                    Example 1: Professional Context<\/strong><\/p>\n
                                    <\/p>\n
                                    \"I'm a customer service manager at an e-commerce company. We've been receiving \ncomplaints about delayed shipping times due to a warehouse transition.\"\n<\/code><\/pre>\n
                                    <\/p>\n
                                    Example 2: Personal Context<\/strong><\/p>\n
                                    <\/p>\n
                                    \"I'm planning my daughter's 10th birthday party. She loves science and has \ninvited 15 friends, mostly from her robotics club.\"\n<\/code><\/pre>\n
                                    <\/p>\n
                                    Example 3: Academic Context<\/strong><\/p>\n
                                    <\/p>\n
                                    \"I'm a college sophomore taking an introduction to psychology course. I need \nto prepare for an exam covering cognitive behavioral therapy.\"\n<\/code><\/pre>\n
                                    <\/p>\n
                                    Before and After: The Power of Context<\/h3>\n
                                    <\/p>\n
                                    Without Context:<\/strong> “Help me write an email.”<\/p>\n
                                    <\/p>\n
                                    The AI doesn’t know: Who are you? Who’s the recipient? What’s the purpose? What tone is appropriate?<\/em><\/p>\n
                                    <\/p>\n
                                    With Context:<\/strong> “I’m a freelance graphic designer. A client missed their payment deadline two weeks ago. We have a good relationship, but I need to send a firm but professional reminder about the $2,500 invoice.”<\/p>\n
                                    <\/p>\n
                                    Now the AI understands your role, relationship, situation, and what’s at stake.<\/em><\/p>\n
                                    \n
                                    \u00a0<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
                                    \n\t\t\t\t\t
                                    \n\t\t\t\t
                                    \n\t\t\t\t
                                    \n\t\t\t\t\t
                                    2. Task: Being Specific About What You Want<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
                                    \n\t\t\t\t
                                    \n\t\t\t\t\t\t\t
                                    \n\t\t\t
                                    <\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
                                    \n\t\t\t\t\t
                                    \n\t\t\t\t
                                    \n\t\t\t\t
                                    \n\t\t\t\t\t\t\t\t\t
                                    Clear Task Definition<\/h3>\n\n
                                    Your task should answer:<\/p>\n\n