The Perfect AI Prompting Framework

First, you have to narrow the AI's knowledge base by specifying its role. For example:

Act as an expert copywriter specializing in engaging social media posts.

Next, you'll need to provide contextual details. This means providing background information to help the AI understand your specific circumstances. You could upload relevant documents, explain the situation, or provide further context.

With the contextual details in place, you can ask AI to help with your question. To avoid sending the AI down a wrong path, focus on one topic at a time for more detailed and relevant answers—keeping your questions specific and targeted.

Finally, let the AI gather any additional information it needs by adding by asking it to request clarifying questions.

Please ask me any clarifying questions that you need to give me the best possible response.

Ready to put your framework to work? Here are three ideas to try:

Let AI Interview You to Help With Ideation

For complex tasks, have the AI interview you. This approach is great for brainstorming, planning projects, or exploring complex topics. Here's how:

Tell the AI to interview you about your topic, then ask it to pose thought-provoking questions to uncover key insights. Be sure to request that it ask no more than three questions at a time.

For example:

Conduct an interview with me to gather insights for creating a compelling 

social media post about why digital agencies need to embrace AI for marketing content creation.

Ask thought-provoking questions that will help uncover the key benefits, challenges,

and future implications of AI adoption in digital marketing agencies. 

Please ask no more than three questions at one time.

Analyze Data to Gain Insights

This can save hours of manual analysis and provide insights you might have missed. Here’s a step-by-step guide on how to use ChatGPT to analyze data in a spreadsheet:

First, organize your clean data in a spreadsheet (Excel, Google Sheets, etc.). 

Next, provide a brief description of your dataset to ChatGPT. For example, tell the AI how many columns and brown exist, describe the types of data (e.g., dates, sales figures, categories), and then provide any specific questions or goals you have for the analysis.

Now, you can use prompts to guide ChatGPT through the analysis. For instance, you can ask ChatGPT for:

Descriptive statistics

Can you calculate the average, maximum, and minimum values for this dataset?

Trend analysis

What trends can you identify in this data over time?

Data categorization

Can you group this data by category and summarize the results?

Once produced, review the insights provided by ChatGPT and ask follow-up questions to dive deeper into any findings.

Today's advice is provided with insights from Jonathan Mast, a featured guest on the AI Explored podcast.