Day 7: Research and share prompt engineering techniques

Woo hoo! We’ve made it to Day 7 of our 30 Days of AI in Testing challenge! :then: This week, we’ve covered a lot of ground in understanding AI concepts, tools, and the real-world impact.

Now, let’s focus on a crucial skill for leveraging AI: prompt engineering. Prompt engineering is the practice of designing prompts to get better outputs from AI. Your challenge today is to uncover and share effective prompt engineering techniques.

Task Steps

  • Research Prompt Engineering: Conduct some research on effective prompt engineering techniques.

  • Share Your Findings: Share 2-3 prompt engineering techniques you found that seem relevant, useful or new to you in reply to this topic. Feel free to link to any helpful resources you found as well.

Here’s an example to guide your response:

  • Prompt technique 1: [name]
  • How it works: [brief description]
  • Potential impact: [how it can improve AI output]
  • Useful resource: https://www.promptingguide.ai/

Why Take Part

  • Enhance AI Interaction: Learning and applying prompt engineering techniques can improve the way you use AI tools, leading to more accurate and relevant outputs.

  • Share and Learn: By sharing your findings and discussing prompt engineering strategies, you contribute to the whole community’s knowledge base, helping others refine their AI interactions.

https://club.ministryoftesting.com/t/day-7-research-and-share-prompt-engineering-techniques/74862

My Day 7 Task

  • Getting Started Prompt: I initially started by mimicking and practicing writing my own prompts through this GitHub project awesome-chatgpt-prompts.

  • Prompt Skill Learning: I utilized a free e-book called “The Art of ChatGPT Prompting: A Guide to Crafting Clear and Effective Prompts” to enhance my prompt crafting skills.

  • Interesting Prompt Philosophy: If you don’t have an idea for an answer, don’t search for a question. Following this principle when composing prompts has been highly effective for me.

  • Prompt Requirements: The art of asking questions involves attempting to clearly describe the problem, articulating both the problem and the desired solution in one go.

  • My Frequently Used Prompt Techniques: The prompts I commonly use now typically include these three components: Background + Constraints + Goal + Expected Answer.

    • Clearly Describe the Background:
    In commonly used prompts, the background usually includes the following information:

- Character (WHO) — including the roles involved in this prompt and relevant characters.
- Location (WHERE) — specifying geographical details may lead to more targeted solutions.
- Event (WHAT) — detailing the specific incident that occurred.
- Time (WHEN) — indicating when the event took place.

    • Clearly Define the Goal: What result do you want from the AI’s response?

    • Introduce Constraints: Human/time/material constraints regarding the described scenario.

    • Lastly, Specify the Expected Answer: For example, request the result in a specific format (markdown, English, Chinese, etc.), or ask for multiple solutions for me to choose the best one.

The community replied resources in the results

About Event

The “30 Days of AI in Testing Challenge” is an initiative by the Ministry of Testing community. The last time I came across this community was during their “30 Days of Agile Testing” event.

Community Website: https://www.ministryoftesting.com

Event Link: https://www.ministryoftesting.com/events/30-days-of-ai-in-testing

Challenges: