Prompt Engineering: A beginner's guide to Persona Prompts

Persona Prompt: Part 3

Unlock the Power of Your AI Assistant as Reviewer

Introduction

In the earlier blog Persona Prompt (Engineering) : Part 1 and Part 2 we learned the basics and advanced techniques for creating Persona Prompt.
In this blog we will learn further a very useful technique to use GenAI (ChatGPT, Gemini etc.) to review contents and provide critical feedback to improve.

Format of a Persona Prompt

You are a LLM. I want you to be a reviewer and provide “XX review” questions to the input i give.

< Input>

—–
Replace the ‘XX Review’ with following options
Skeptical Review: Offering skeptical feedback to the content to ponder further.
Constructive Review: Offering feedback that not only critiques but also suggests improvements or alternative approaches.
Analytical Review: Breaking down the content into its constituent parts to understand the underlying structure and implications.
Comparative Review: Evaluating the content in comparison to other similar works or theories, highlighting differences and similarities.
Historical Contextual Review: Placing the content within its historical context to understand its significance and impact over time.
Theoretical Review: Examining the theoretical foundations of the content and its contribution to the field of study it pertains to.

<Input> Can be a statement, a claim, a piece of data, an idea – anything you want to put under a review microscope.

Let’s See Some Examples!

Best Practices

Leverage various ‘Review’ types as AI persona and ask it to challenge your thoughts and inputs.
You can also combine various review types in one prompt e.g. As a reviewer provide both skeptical and constructive feedback on the input I provide ….

Let Your AI Wear Many Hats?

Persona prompts are a simple but incredibly powerful tool to make your AI assistant more versatile and helpful. Now go try it yourself and see how you can make your AI work smarter for you!

Disclaimer!

LLM like ChatGPT, Gemini can provide incorrect and inaccurate outputs. Always double check the output before you use it.

Have a question?

If you have any other queries, feel free to reach out to me or drop a comment.

Learn More !

Experiment directly with ChatGPT and Google Gemini.
Want to learn more about effective prompts to get the best out of GenAI and LLMs?

Home Prompt Engineering

Discover more from Debabrata Pruseth

Subscribe to get the latest posts sent to your email.