Real-world use cases

Discover how prompt engineering can be applied to a wide variety of tasks. These examples showcase the versatility of LLMs when guided by well-crafted prompts.

Content creation (blog post outline)

Generate outlines, drafts, or ideas for various types of content like blog posts, articles, marketing copy, or social media updates.

Example prompt:

Create a blog post outline for an article titled 'the future of remote work', targeting an audience of HR professionals. Include an introduction, 3 main body sections with sub-points, and a conclusion.

Conceptual output:

## The future of remote work: an HR perspective

**Introduction**
  - Brief overview of the shift towards remote work
  - Importance for HR professionals to adapt and strategize

**Section 1: the evolving landscape of remote work**
  - Current trends and statistics
  - Technological enablers (collaboration tools, cloud computing)
  - Employee expectations and desires

**Section 2: HR challenges and opportunities in a remote-first world**
  - Talent acquisition and onboarding (broader talent pool, virtual onboarding)
  - Employee engagement and culture (maintaining connection, virtual team building)
  - Performance management and productivity (metrics, trust, well-being)
  - Legal and compliance considerations (multi-state employment, data security)

**Section 3: strategies for HR to thrive in the future of remote work**
  - Developing robust remote work policies
  - Investing in technology and training
  - Fostering a strong remote culture
  - Focusing on employee well-being and mental health

**Conclusion**
  - Recap of key takeaways
  - Call to action for HR leaders to proactively shape the future of work

Tips for success:

  • Specify the target audience, tone, and desired length/format.
  • Provide keywords or key themes to include.
  • Use it for brainstorming and then refine the generated content.

Text summarization

Condense long documents, articles, or conversations into concise summaries, extracting key information and main points.

Example prompt:

Summarize the following article into 3 key bullet points. The article discusses the impact of artificial intelligence on the healthcare industry, focusing on diagnostics, drug discovery, and personalized medicine.
[Paste a lengthy article snippet here about AI in healthcare]

Conceptual output:

Key bullet points:
* AI is revolutionizing healthcare diagnostics by enabling faster and more accurate detection of diseases from medical imaging.
* In drug discovery, AI algorithms are significantly speeding up the process of identifying potential drug candidates and predicting their efficacy.
* Personalized medicine is advancing through AI's ability to analyze patient data and tailor treatment plans to individual needs.

Tips for success:

  • Specify the desired length or format of the summary (e.g., one paragraph, bullet points).
  • Indicate if you want an abstractive (rephrased) or extractive (key sentences) summary.
  • For very long texts, you might need to summarize in chunks.

Question answering (closed domain)

Answer questions based on a provided context or document. Useful for creating FAQs from internal knowledge bases.

Example prompt:

Context: the company's standard vacation policy allows for 20 paid days off per year for full-time employees. Employees accrue 1.67 days per month. New employees are eligible after a 90-day probationary period.

Question: how many vacation days does a new full-time employee get after working for 6 months, and when can they start taking them?

Conceptual output:

Based on the policy:
- after 6 months, a full-time employee would have accrued 6 * 1.67 = 10.02 days (approximately 10 days) of vacation.
- they can start taking vacation days after completing their 90-day probationary period.

Tips for success:

  • Clearly separate the context/document from the question.
  • Ensure the answer is directly inferable from the provided text.
  • For open-domain Q&A (general knowledge), less context might be needed, but specificity in the question is still key.

Creative writing (story idea)

Brainstorm story ideas, character descriptions, plot points, or even generate short pieces of creative writing.

Example prompt:

Generate three distinct story ideas for a science fiction novel set in a future where water is the most valuable currency. Each idea should include a protagonist, a central conflict, and a potential theme.

Conceptual output:

Story idea 1:
  - Protagonist: a young, resourceful scavenger living on the arid outskirts of a domed city.
  - Conflict: she discovers a hidden, uncorrupted natural spring but must protect it from a ruthless water baron who controls the city's supply.
  - Theme: environmentalism, corporate greed vs. individual survival.

Story idea 2:
  - Protagonist: an aging starship captain who transports ice asteroids to Earth.
  - Conflict: during a routine haul, his ship is attacked by pirates who steal not just water, but a secret map to a mythical 'water planet'. He must retrieve it.
  - Theme: resource scarcity, adventure, the cost of desperation.

Story idea 3:
  - Protagonist: a scientist within a sealed underwater research facility that purifies saltwater.
  - Conflict: he uncovers a conspiracy that the facility is intentionally restricting water output to maintain high prices, while a deadly drought ravages the surface world.
  - Theme: moral dilemma, whistleblowing, societal inequality.

Tips for success:

  • Provide genres, themes, character archetypes, or specific elements you want to include.
  • Ask for multiple variations to get a range of ideas.
  • Use a higher temperature setting for more novel and unexpected creative outputs.

Code generation

LLMs can generate code snippets, functions, or even entire applications in various programming languages based on natural language descriptions.

Example prompt:

Write a Python function that takes a list of integers and returns a new list containing only the even numbers.

Conceptual output:

def get_even_numbers(numbers):
  even_numbers = []
  for number in numbers:
    if number % 2 == 0:
      even_numbers.append(number)
  return even_numbers

# Example usage:
print(get_even_numbers([1, 2, 3, 4, 5, 6]))
# Output: [2, 4, 6]

Tips for success:

  • Be specific about the programming language, libraries, and desired functionality.
  • Provide examples of input and expected output if possible (few-shot).
  • For complex code, break down the request into smaller, manageable parts.
  • Always review and test generated code thoroughly.

Code explanation

Understand complex code snippets or functions by asking the LLM to explain them in plain language.

Example prompt:

Explain what this JavaScript code does, line by line:
```const greet = (name) => {
  return `Hello, ${name}!`;
};
console.log(greet('World'));```

Conceptual output:

Explanation:
1. `const greet = (name) => {`: this line declares a constant variable named 'greet' and assigns it an arrow function. This function accepts one parameter called 'name'.
2. `  return `Hello, ${name}!`;`: inside the function, this line returns a string that concatenates "Hello, " with the value of the 'name' parameter and an exclamation mark. It uses a template literal for easy string interpolation.
3. `};`: this closes the function definition.
4. `console.log(greet('World'));`: this line calls the 'greet' function with the argument "World" and prints the returned value ("Hello, World!") to the console.

Tips for success:

  • Provide the full code snippet you want explained.
  • Ask for explanations at different levels of detail (e.g., high-level overview vs. line-by-line).
  • Specify the programming language if it might be ambiguous.

These are just a few examples! The possibilities are vast. The key is to understand your goal, choose the right prompting techniques, and iterate based on the results.

Hungry for more? Visit our blog for the latest AI & prompt engineering tips, tricks, and deep dives!

Visit our blog
    promptengineering.be

    Discover high-quality prompts for ChatGPT, Midjourney, and other AI tools to enhance your creativity and productivity.

    Quick links

    • Categories
    • Prompts
    • Packs

    Learn

    • Prompting basics
    • Prompting advanced
    • Use cases
    • Our blog
    • About us

    Legal

    • Privacy
    • Terms
    • Contact

    © 2025 promptengineering.be - All rights reserved.

    PrivacyTermsContact
      promptengineering.be logopromptengineering.be
      Login