Skip to main content

Prompt Engineering

Prompt Engineering simply means asking good questions to the AI. A prompt is your input with your question or request.

Prompt engineering involves designing targeted questions and instructions to help AI models provide the right answers during chats. With better prompts, you get better results.

Together with the specifications of the chosen model, this determines the quality of the answer.

Elements of a Prompt (Question)​

To get better results, you should consider the following points:

  • Objective: What exactly do you want from the language model?
  • Role: What role does the language model have? (E.g. 'Marketing Analyst', 'Legal Advisor', 'Project Manager')
  • Context: Background information about the request (E.g. business objectives, project details, market information)
  • Style: What style do you want to use? (E.g. formal, persuasive, concise)
  • Output: What format do you want? (E.g. a report, email, presentation outline, code snippet)

The Objective​

Precisely describing the objective of your question is essential and cannot be omitted.

What do you want to know?

  • Fact questions are possible, but be aware of the limitations (e.g., current knowledge is missing)
  • Similar to Google, you won't get exactly the same answer if you ask the question multiple times
  • The advantage is the "chat" function so you can ask follow-up questions

Example prompt with a clear objective:

Prompt with only objective

Provide a description of the key challenges for implementing a new AI platform in a medium-sized company.

Implementing a new AI platform in a medium-sized company brings various challenges. Some key challenges are:

  1. Resistance to change: Employees are accustomed to existing processes and systems. A new AI platform requires adaptation and can provoke resistance, especially if the impact on workflows is not clear.
  2. Data quality and availability: AI platforms are highly dependent on data. Collecting, cleaning, and structuring data for the new platform can be complex and time-consuming.
  3. Integration with existing systems: The AI platform often needs to be integrated with other business applications (ERP, data sources, BI tools). This can present technical challenges.
  4. Costs: In addition to platform license costs, there are expenses for implementation, training, data infrastructure, and possibly specialized personnel.
  5. Training and adoption: Employees must be trained in using the new platform and interpreting its output. Without good training and continuous support, the adoption rate can remain low.
  6. Choosing the right platform and use cases: There are many AI platforms and technologies. Selecting a platform and defining relevant use cases that fit the specific needs and strategic goals of the company is crucial.
  7. Ethical considerations and compliance: Depending on the AI platform's application, there may be ethical issues and compliance requirements (e.g., GDPR) that must be carefully addressed.
  8. Project management: A successful implementation requires thorough project management, clear objectives, and stakeholder involvement from different departments.

Adding Role and Context​

Adding a role and context ensures better and more specific answers.

Example of the same question but with role and context:

Prompt with objective, role, and context

As a project manager responsible for implementing a new AI platform for data analysis and process optimization at a B2B service provider with 150 employees, provide a description of the key challenges and possible mitigation strategies.

As a project manager for implementing a new AI platform for data analysis and process optimization at a B2B service provider with 150 employees, I see the following key challenges and possible mitigation strategies:

[The rest of the document continues in the same translated manner, maintaining all markdown formatting, code blocks, and technical terms.]