Even after achieving results you can use, it is still a good idea to evaluate the response. Andrew Maynard describes the RACCCA method of evaluation. This type of evaluation can help you improve your future prompts.

Bonus: these prompts are templates. They can be re-used easily by just changing the information for the bracketed terms at the bottom of each prompt.

Evaluation Prompt

In Microsoft Copilot/Bing or ChatGPT, try this after you receive a response to your original prompt:

Assess the quality of the response using the RACCCA scale, include a quantitative metric on the scale of 1-5 with 5 being the highest rank. Place the evaluation in a table

You are looking for higher numbers on a scale of 1-5; read the Andrew Maynard article to understand why.

Detailed Evaluation Prompt

For a more comprehensive evaluation, open a second chatbot and use this prompt, pasting in your original request and the response where indicated.

In response to the question [question] I got the following response: [response]. Please assess this response in terms of: Relevance (The extent to which the response directly addresses the issue or question); Accuracy (The degree to which the response provides correct, reliable, and fact-based information); Completeness (The degree to which the response covers all essential aspects of the topic or question being asked); Clarity (How easily the response can be understood by the intended audience); Coherence (The extent to which the response is logically structured and well-organized and flows smoothly from one point to another); and Appropriateness (How well the response aligns with the intended audience and context and is suitable and respectful in tone and content).
[question]: paste here
[response]: paste here

How to Achieve Better Results to Original Question

As a follow-up, ask your chatbot to then come up with better prompts

Please provide me with five alternatives to the prompt [prompt] that will substantially increase the quality of your response based on the RACCCA framework. The RACCCA framework refers to Relevance (The extent to which the response directly addresses the issue or question); Accuracy (The degree to which the response provides correct, reliable, and fact-based information); Completeness (The degree to which the response covers all essential aspects of the topic or question being asked); Clarity (How easily the response can be understood by the intended audience); Coherence (The extent to which the response is logically structured and well-organized and flows smoothly from one point to another); and Appropriateness (How well the response aligns with the intended audience and context and is suitable and respectful in tone and content).
[prompt]: paste here

Evaluation Prompt (again)

Then run results through the evaluation prompt again.

In response to the question [question] I got the following response: [response]. Please assess this response in terms of: Relevance (The extent to which the response directly addresses the issue or question); Accuracy (The degree to which the response provides correct, reliable, and fact-based information); Completeness (The degree to which the response covers all essential aspects of the topic or question being asked); Clarity (How easily the response can be understood by the intended audience); Coherence (The extent to which the response is logically structured and well-organized and flows smoothly from one point to another); and Appropriateness (How well the response aligns with the intended audience and context and is suitable and respectful in tone and content).

Image Prompt

This Adobe Firefly image generation riffs off the original generated by Jefferson Lima. It is easy to find inspiration by scrolling through the contributions of other creators on the Firefly site!

Portrait in 17th century oil painting, finger of one hand touching lip showing indecision, at a lake in early summer with mist and sunrise in the background, lightness, brushstrokes, airy, fresh and soft