Promt software engineer rEngineering.pdf

Unleashing the Power of Gen AI
Prompt Engineering
Proprietary content. ©Great Learning. All Rights Reserved. Unauthorized use or distribution prohibited.

Agenda
In this session, we’ll discuss:
● Introduction to Generative AI and LLMs
● Basics of Prompt Engineering
● Components of a Good Prompt
● How to Write a Prompt?
● Advanced Prompt Strategies
● Common Prompting Errors
● Limitations of Generative Models
● Applications of Prompt Engineering

Introduction to Generative AI (Gen AI)
Generative AI (Gen AI) refers to Artificial Intelligence that can generate
content — be it text, images, or code — based on the input it receives from
the user.

Understanding Gen AI
LLM
Artificial
Intelligence
Machine
Learning
Deep
Learning
Gen AI
ChatGPT is here

Introduction to Large Language Models (LLMs)
What are LLMs?
● Large – as it is trained on large amounts of data and billions of trainable parameters.
● Language – as it deals with text data.
● Model – as it predicts the next word/sentence/token.
● LLMs are language models made up of a neural network with billions of parameters that are trained by
self-supervised learning on vast amounts of unlabeled text.
Foundational LLMs like GPT-3
Base LLMs
Task-specific models following
provided directives
Instruction-
based LLMs
LLMs

Introduction to Large Language Models (LLMs)
How do LLMs work?
Tasks
1. Text Summarization
2. Sentiment Analysis
3. Question Answering
4. Information Extraction
5. Text Translation
Text
Input LLMs
Generative
Models
Pre-training Fine-tuning

Popular LLMs
GPT by OpenAI Gemini by Google Llama by Meta
Mistral by OpenAI

Basics of Prompt Engineering
Prompt engineering is as much an art as it is a
science.
Prompt: A detailed set of guidelines given to an
LLM to do a task.
Engineering: Developing a task-specific prompt
iteratively.
Prompt Engineering is an iterative process.
Idea
Test or
Feedback
Prompt
Results

Basics of Prompt Engineering
Prompts
Parameters
1
Structure
2
1. Temperature: Lower for creativity and deterministic results; Higher for
diversity and factual QA.
2. Top P: Control model determinism; Low for factual, high for diverse.
3. Max Length: Manage response length.

Let’s write a few prompts!!

Components of a Good Prompt
external information or
Additional context that
can steer the model to
better responses.
Context
The input or question
that we are interested in
finding a response for.
Input Data
A specific task or
instruction you want the
model to perform.
Instruction
The type or format of the
output.
Output Indicator

Context
Act as an analyst working for an OTT platform. You will have to perform
sentiment analysis based on the feedback provided by the consumers on
the movies and series put on the OTT platform.
better responses.
Context

Instruction
Classify the feedback as neutral, negative, or
positive, where positive is promotor; negative
means demoter, and neutral means neither
will promote nor demote the content.
better responses.
Context
A specific task or
model to perform.
Instruction

Example
Feedback: I think the series was okay.
Sentiment: Neutral
Feedback: The acting of each character in the
series was awesome.
Sentiment: Positive
Input Data and Output Indicator
Feedback: The storyline for the series was
repetitive and abysmal.
Sentiment:
better responses.
Context
The input or question
that we are interested in
finding a response for.
Input Data
A specific task or
model to perform.
Instruction
The type or format of the
output.
Output Indicator

Example
Feedback: I think the series was okay.
Sentiment: Neutral
Feedback: The acting of each character in the
series was awesome.
Sentiment: Positive
Input Data and Output Indicator
Feedback: The storyline for the series was
repetitive and abysmal.
Sentiment:
Negative
Instruction
Classify the feedback as
neutral, negative, or
positive, where positive is
promotor; negative
means demoter, and
neutral means neither
will promote nor demote
the content.
Context
Act as an analyst
working for an OTT
platform. You will have
to perform sentiment
analysis based on the
feedback provided by
the consumers on the
movies and series put
on the OTT platform.

How to Write a Good Prompt?
● Define the Goal – Tell ChatGPT what you exactly want it to do.
● Detail out the Format – Specify the format in which you want your output. E.g., tables/paragraphs/lists,
with or without a heading, listed in priority order if any, etc.
● Create a Role – Assign ChatGPT a role to let it process your request from that specific point of view.
E.g., Act as X.
● Clarify who the Audience is – Specify the demographics for ChatGPT to help it tailor its response
appropriately.
● Give Context – Provide every possible information to ChatGPT to help it understand the purpose of
your request.
Here’s a checklist, to create the most effective prompt and get the best results.

How to Write a Good Prompt?
● Give Examples – Share examples to let ChatGPT learn from it and produce more accurate results.
● Specify the Style – Outline the tone, the communication style, the brand identity and other details in
your prompt for a suitable response.
● Define the Scope – Outlining a scope with further specifications besides giving a context and examples,
will help ChatGPT operate within those parameters.
● Apply Restrictions – Constraints or restrictions applied in your prompt will create the right boundaries
for ChatGPT to produce more relevant responses.
Here’s a checklist, to create the most effective prompt and get the best results.

Different Prompt Patterns
What are some of the most common Prompt Patterns?
1. Persona Pattern - Act as X. Do the task Y. (E.g., As a Yoga instructor, create a beginner-friendly routine for joint
mobility.)
2. Audience Persona Pattern - Explain X to me. Assume I’m Y. (E.g., Explain the importance of eating greens. Assume
I’m a skeptical child.)
3. Visualization Generator Pattern - Generate X that can be provided to tool Y for visualization. (E.g., While talking
about the data around user engagement metrics on certain website, generate a CSV that I can use in Tableau to
create a visualization.)

Different Prompt Patterns
4. Recipe Pattern - In order to do X, I need to perform steps a, b, c. Provide a complete sequence of steps for me
while filling in any missing steps and removing redundant steps. (Eg: I want to travel from Bangalore to Darjeeling. I
know I have to take a flight to Kolkata. And from there take train and a cab to Darjeeling. Complete the itinerary
for me)
5. Template Pattern - I will provide a template, with placeholders for content. Fit the output with one or more
placeholders that I list.
Eg: Generate a day-wise travel itinerary for visiting Paris.
My placeholders are -
❏ <Day> for the day of the travel plan
❏ <Location> for the place to visit
❏ <Activity> for what to do in that place
❏ <Time> for the best part of the day to visit
Template: For <Day> visit <Location> at <Time> for <Activity>
What are some of the most common Prompt Patterns?

Examples

Advanced Prompt Strategies
● Zero-Shot Learning - Directly instructing the model to perform a task without any additional examples.
● Few-Shot Learning – Teaching with examples in the prompt.
● Chain of Thought Process – Asking to show its work or thought process.
Here’s a few instances of advanced prompt strategies:

Common Prompting Errors
1. Vague or Ambiguous Prompts
2. Biased Prompts
3. Lack of Contextual Information
4. Insufficient Examples or Training Data
5. Complex or Confusing Prompts
6. Not testing prompts thoroughly

Limitations of Generative Models
1. Hallucinations - produce imaginative and surreal responses
2. Token length - tokens available 4096 tokens for input & 2048 for output
3. Pricing - for better versions / increase in token size
4. Resource Intensive - computationally expensive and resource-intensive

Applications of Prompt Engineering
Content
Generation
Data Analysis and
Science
Code Generation
and Software
Development
Research and
Information
Retrieval
Customer Support
and Engagement
- Automating Code Writing
- Debugging Assistance
- Documentation Generation
- Text Summarization
- Question Answering
- Chatbots and Virtual
Assistants
- Instructional Guides
- Copywriting and Advertising
- Creative Writing
- Educational Content
- Data Cleaning and
Preparation
- Statistical Analysis and
Visualization

Applications of Prompt Engineering
Machine
Translation
Other
Domains
Sentiment
Analysis
- Consumer Feedback Analysis
- Brand Management
- Marketing
- Information Sharing
- Internal Communication
- Healthcare
- Manufacturing
- Security
- Retail and Shopping

Summary
Here’s a brief recap:
● The key to becoming a proficient prompt engineer is practice.
○ Experiment with different prompts.
○ Analyze the outcomes.
○ Refine your techniques.
● Keep practicing, stay curious, and explore various AI platforms to enhance your skills.

Promt software engineer rEngineering.pdf

Related slideshows

More Related Content

Similar to Promt software engineer rEngineering.pdf

Similar to Promt software engineer rEngineering.pdf (20)

Promt software engineer rEngineering.pdf