Scribd
Upload
7 views2 pages

Art of Prompting

The document discusses prompt engineering, which is the practice of designing effective prompts to elicit useful outputs from large language models (LLMs). It outlines key principles for writing effective prompts, including clarity, context, and evaluation of outputs, as well as the iterative process of refining prompts based on AI responses. Additionally, it highlights various applications of LLMs in content creation tasks.

Uploaded by

teacherbiancarivera
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
7 views2 pages

Art of Prompting

The document discusses prompt engineering, which is the practice of designing effective prompts to elicit useful outputs from large language models (LLMs). It outlines key principles for writing effective prompts, including clarity, context, and evaluation of outputs, as well as the iterative process of refining prompts based on AI responses. Additionally, it highlights various applications of LLMs in content creation tasks.

Uploaded by

teacherbiancarivera
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 2

===================================================================================

==================

by Yufeng, Developer Relations Engineer at Google Cloud

PROMPT - text input that provides instructions to the AI model on how to generate
output

Prompt engineering involves designing the best prompt you can to get the output you
want.
-is the practice of developing effective prompts that elicit useful output from
generative AI

ITERATION
few-shot prompting

===================================================================================
==================

LLM - large language models


-is an AI model that is trained on large amounts of text to identify patterns
between words, concepts, and phrases, so that it can generate responses to prompts
-are powerful tools that require human guidance for effective use

**An LLM may vary in its response to the same prompt each time you use it.

Hallucinations are AI outputs that are not true


-the quality of an LLM's training data
-the phrasing of the prompt
-the method an LLM uses to analyze text and predict the next word in a sequence

===================================================================================
==================
===================================================================================
==================

KEY PRINCIPLES OF EFFECTIVE PROMPT WRITING


1. Write clear and specific prompts
2. Prompting best practices
3. Leverage an LLM's capabilities at work
4. Prompts for different purposes
5. Improve AI output through iteration

Prompting best practices


-Specify the task - the foundation of every prompt
**Task
-Persona
-Format
-Provide necessary context
-Reasons and objectives for performing the task
-Rules or guidelines that the output must follow
-Relevant background information the tool should consider
-Include references as examples
-Briefly explain how the references relate to the task.
-Use 2-5 high-quality examples that closely align with your needs.
-Include your own work or open-source examples if relevant.
-Evaluate your output
-Accuracy
-Bias
-Relevancy
-Consistency

===================================================================================
==================
===================================================================================
==================

TYPICAL FLOW

You provide an initial prompt.


The AI tool responds with an output.
You evaluate the effectiveness of the AI-generated response.
You refine your request based on what worked and what didn't.
The cycle repeats until you produce the desired results.

===================================================================================
==================

Pro Tip: When you've arrived at an effective prompt for a particular task, save it!
You can use your most effective prompts as templates for different use cases and
needs. This can help you replicate successful AI-output consistently—without
starting from scratch each time.

===================================================================================
==================
===================================================================================
==================
===================================================================================
==================

Content creation
-Create outline
-Summarize
-Classification
-Data extraction
-Translate
-Problem-solving

===================================================================================
==================

You might also like