Leveraging Generative AI & Best practices

Leveraging
Generative AI
Ashling Partners | Solutions Engineering | Alp Uguray, 4x UiPath MVP
2
Senior Solutions Engineer at Ashling Partners
4x UiPath MVP Award
Host & Creator at Masters of Automation Podcast
(https://themasters.ai)
Alp Uguray
Introductions
Innovation Ambition Matrix
HOW TO WIN
WHERE
TO
PLAY
TRANSFORMATIONAL
Large market opportunity identified
but very different from what we are
doing today.
ADJACENT
Not doing today, but plugs right into
what we are doing today
CORE
Already doing it today
Develop New
Products & Assets
Add incremental
Products & Assets
Use Existing
Products & Assets
Serve
existing
Markets
&
Customers
Enter
Adjacent
Markets
Serve
Adjacent
Customers
Create
New
Market
Target
New
Customers
4
5
Good ones (Utopic Use)
• Leverages AI versus. Manual execution productivity gains
• Augmentation in task execution as HITL suggestions and recommendations
Not so good ones (Most likely)
• Job Displacement / Re-write
• Digital Misuse
• Digital Divide
• Vulnerability increase with cyberattacks
Worst ones (Cautious view)
• Data Privacy
• Fake Content and IP Law
• Failure of Regulations
• LLMs dominate the communication lines - Don’t know who you speak and widespread
adoption of personalized Face, Voice and Text
Importance of Scenario Planning
Driven by productivity gains and improved Customer and Employee Experiences,
Conversational AI dominance depends on a few different outcomes based on its adoption
6
Focus on realistic applications that can complement existing business capabilities.
• Prioritize applications based on ease of implementation and risk level, gradually moving towards more complex and
valuable ones. An example of a key application is using generative AI for knowledge management, which can provide
immediate value across various business functions
Do not have a perfectionist attitude towards the development of AI applications, which
could trap you in the proof-of-concept phase without ever delivering value.
• An iterative product development approach where applications are developed to solve specific customer or employee
problems and are then continuously adjusted based on feedback until they're ready to be scaled. This ensures that the
efforts have purpose and contribute towards transforming the industry standards​
The importance of ensuring that AI adoption doesn't compromise the organization's
data and intellectual property security, customer data security, brand credibility, and
legal protections.
• Collaboration between leaders from operations, technology and data teams, and the legal department to create
guardrails that empower the organization without hindering it.
Some Guiding Principles in Adoption
What’s prompt engineering?
Prompt engineering is the ‘art’ of optimizing
natural language for a LLM. Effective prompts
provide the relevant context and detail to a LLM,
therefore improving the accuracy and relevance
of the response.
The quality of prompts directly affects the output
of the model. Effective prompts help the model
understand your request and generate
appropriate responses, in complex or ambiguous
scenarios.
Tips / Tricks –
• Zero-shot Learning: never seen your data,
but makes inferences based on
understanding
• CoT (chain-of-thought) reasoning, ‘break it
down, step-by-step’
• Providing relevant context, ‘I am’ or ‘you are’
• First, do ‘xyz’, then do ‘xyz’, finally…
8
Zero-shot learning
This is a problem set up in machine learning where the model is asked to classify data
accurately it has never seen before during training. In other words, the model is expected
to infer classes that were not part of its training data. The model typically leverages high-
level abstractions and understandings learned from the training data to make accurate
predictions on the unseen classes. Zero-shot learning is especially important in settings
where it is costly or time-consuming to collect large labeled datasets for every possible
class.
Few-shot learning
Few-shot learning refers to the concept where a machine learning model is able to
generalize well from a small number of examples – often just one or two, hence the term
"one-shot" or "two-shot" learning. In a traditional machine learning context, models are
often trained on large amounts of data, but in few-shot learning, the idea is to design
models that can extract useful information from a small number of examples and make
accurate predictions. This is similar to how humans can often learn concepts from just a
few examples.
Shot Learnings
Some considerations
Data privacy and security:
• Avoid using real customer data or any personally
identifiable information (PII).
• Use anonymized or synthetic data sets whenever
possible.
• Ensure data storage and transfer follow best practices
and comply with relevant regulations, such as GDPR
or HIPAA.
“Hallucinations” - ChatGPT can make stuff up.
• Be aware of potential biases in data sets and
algorithms, which could lead to unfair or
discriminatory outcomes.
• Use techniques such as data pre-processing or
algorithmic adjustments to minimize the impact of
biases.
Responsible use of AI:
• Ensure that your solution aligns with ethical principles
and responsible AI guidelines.
• Avoid applications that could be harmful,
discriminatory, or promote misinformation.
10
Reinforcement
Learning
Prompt
Engineering
Chain of
Thought
How to get the best out of AGIs
11
RLHF
Reinforcement learning from human
feedback further aligns models.
(Diagram from OpenAI ChatGPT
announcement.)
12
Prompting with the “format trick”
“Use this format:” is all you need.
©
2
0
2
3
S
c
a
l
e
I
n
c
.
13
Specifying tasks using
code prompts
Prompting through partial code.
©
2
0
2
3
S
c
a
l
e
I
n
c
.
14
Specifying tasks using
code prompts
Prompting with imaginary variables.
©
2
0
2
3
S
c
a
l
e
I
n
c
.
15
Using an external interpreter to
overcome model limitations in
conversational Q&A.
“You are GPT-3”
©
2
0
2
3
S
c
a
l
e
I
n
c
.
16
Chain-of-thought prompting
Figure 1 from Jason Wei et al. (2022).
©
2
0
2
3
S
c
a
l
e
I
n
c
.
17
Zero-shot
chain-of-thought
Figure 1 from Takeshi Kojima et al. (2022).
©
2
0
2
3
S
c
a
l
e
I
n
c
.
18
Zero-shot
chain-of-thought
Figure 2 from Takeshi Kojima et al. (2022).
©
2
0
2
3
S
c
a
l
e
I
n
c
.
19
Zero-shot
chain-of-thought
Figure 2 from Takeshi Kojima et al. (2022).
©
2
0
2
3
S
c
a
l
e
I
n
c
.
20
Self-consistency
and consensus
Figure 1 from Xuezhi Wang et al. (2022).
©
2
0
2
3
S
c
a
l
e
I
n
c
.
21
Q&A
1 sur 21

Recommandé

Unlocking the Power of Generative AI An Executive's Guide.pdf par
Unlocking the Power of Generative AI An Executive's Guide.pdfUnlocking the Power of Generative AI An Executive's Guide.pdf
Unlocking the Power of Generative AI An Executive's Guide.pdfPremNaraindas1
2.2K vues29 diapositives
Generative-AI-in-enterprise-20230615.pdf par
Generative-AI-in-enterprise-20230615.pdfGenerative-AI-in-enterprise-20230615.pdf
Generative-AI-in-enterprise-20230615.pdfLiming Zhu
843 vues7 diapositives
Using the power of Generative AI at scale par
Using the power of Generative AI at scaleUsing the power of Generative AI at scale
Using the power of Generative AI at scaleMaxim Salnikov
910 vues31 diapositives
How Does Generative AI Actually Work? (a quick semi-technical introduction to... par
How Does Generative AI Actually Work? (a quick semi-technical introduction to...How Does Generative AI Actually Work? (a quick semi-technical introduction to...
How Does Generative AI Actually Work? (a quick semi-technical introduction to...ssuser4edc93
962 vues14 diapositives
Generative AI and law.pptx par
Generative AI and law.pptxGenerative AI and law.pptx
Generative AI and law.pptxChris Marsden
631 vues60 diapositives
GENERATIVE AI, THE FUTURE OF PRODUCTIVITY par
GENERATIVE AI, THE FUTURE OF PRODUCTIVITYGENERATIVE AI, THE FUTURE OF PRODUCTIVITY
GENERATIVE AI, THE FUTURE OF PRODUCTIVITYAndre Muscat
6.6K vues19 diapositives

Contenu connexe

Tendances

An Introduction to Generative AI par
An Introduction  to Generative AIAn Introduction  to Generative AI
An Introduction to Generative AICori Faklaris
11.4K vues28 diapositives
Cavalry Ventures | Deep Dive: Generative AI par
Cavalry Ventures | Deep Dive: Generative AICavalry Ventures | Deep Dive: Generative AI
Cavalry Ventures | Deep Dive: Generative AICavalry Ventures
581 vues18 diapositives
AI FOR BUSINESS LEADERS par
AI FOR BUSINESS LEADERSAI FOR BUSINESS LEADERS
AI FOR BUSINESS LEADERSAndre Muscat
928 vues25 diapositives
Generative AI, WiDS 2023.pptx par
Generative AI, WiDS 2023.pptxGenerative AI, WiDS 2023.pptx
Generative AI, WiDS 2023.pptxColleen Farrelly
3K vues16 diapositives
Large Language Models - Chat AI.pdf par
Large Language Models - Chat AI.pdfLarge Language Models - Chat AI.pdf
Large Language Models - Chat AI.pdfDavid Rostcheck
695 vues19 diapositives
Conversational AI and Chatbot Integrations par
Conversational AI and Chatbot IntegrationsConversational AI and Chatbot Integrations
Conversational AI and Chatbot IntegrationsCristina Vidu
436 vues24 diapositives

Tendances(20)

An Introduction to Generative AI par Cori Faklaris
An Introduction  to Generative AIAn Introduction  to Generative AI
An Introduction to Generative AI
Cori Faklaris11.4K vues
Conversational AI and Chatbot Integrations par Cristina Vidu
Conversational AI and Chatbot IntegrationsConversational AI and Chatbot Integrations
Conversational AI and Chatbot Integrations
Cristina Vidu436 vues
An Introduction to Generative AI - May 18, 2023 par CoriFaklaris1
An Introduction  to Generative AI - May 18, 2023An Introduction  to Generative AI - May 18, 2023
An Introduction to Generative AI - May 18, 2023
CoriFaklaris1939 vues
Exploring Opportunities in the Generative AI Value Chain.pdf par Dung Hoang
Exploring Opportunities in the Generative AI Value Chain.pdfExploring Opportunities in the Generative AI Value Chain.pdf
Exploring Opportunities in the Generative AI Value Chain.pdf
Dung Hoang271 vues
ChatGPT, Foundation Models and Web3.pptx par Jesus Rodriguez
ChatGPT, Foundation Models and Web3.pptxChatGPT, Foundation Models and Web3.pptx
ChatGPT, Foundation Models and Web3.pptx
Jesus Rodriguez807 vues
𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐯𝐞 𝐀𝐈: 𝐂𝐡𝐚𝐧𝐠𝐢𝐧𝐠 𝐇𝐨𝐰 𝐁𝐮𝐬𝐢𝐧𝐞𝐬𝐬 𝐈𝐧𝐧𝐨𝐯𝐚𝐭𝐞𝐬 𝐚𝐧𝐝 𝐎𝐩𝐞𝐫𝐚𝐭𝐞𝐬 par VINCI Digital - Industrial IoT (IIoT) Strategic Advisory
𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐯𝐞 𝐀𝐈: 𝐂𝐡𝐚𝐧𝐠𝐢𝐧𝐠 𝐇𝐨𝐰 𝐁𝐮𝐬𝐢𝐧𝐞𝐬𝐬 𝐈𝐧𝐧𝐨𝐯𝐚𝐭𝐞𝐬 𝐚𝐧𝐝 𝐎𝐩𝐞𝐫𝐚𝐭𝐞𝐬𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐯𝐞 𝐀𝐈: 𝐂𝐡𝐚𝐧𝐠𝐢𝐧𝐠 𝐇𝐨𝐰 𝐁𝐮𝐬𝐢𝐧𝐞𝐬𝐬 𝐈𝐧𝐧𝐨𝐯𝐚𝐭𝐞𝐬 𝐚𝐧𝐝 𝐎𝐩𝐞𝐫𝐚𝐭𝐞𝐬
𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐯𝐞 𝐀𝐈: 𝐂𝐡𝐚𝐧𝐠𝐢𝐧𝐠 𝐇𝐨𝐰 𝐁𝐮𝐬𝐢𝐧𝐞𝐬𝐬 𝐈𝐧𝐧𝐨𝐯𝐚𝐭𝐞𝐬 𝐚𝐧𝐝 𝐎𝐩𝐞𝐫𝐚𝐭𝐞𝐬
Generative AI: Past, Present, and Future – A Practitioner's Perspective par Huahai Yang
Generative AI: Past, Present, and Future – A Practitioner's PerspectiveGenerative AI: Past, Present, and Future – A Practitioner's Perspective
Generative AI: Past, Present, and Future – A Practitioner's Perspective
Huahai Yang563 vues
Responsible Generative AI par CMassociates
Responsible Generative AIResponsible Generative AI
Responsible Generative AI
CMassociates243 vues
The Five Levels of Generative AI for Games par Jon Radoff
The Five Levels of Generative AI for GamesThe Five Levels of Generative AI for Games
The Five Levels of Generative AI for Games
Jon Radoff2.8K vues
Let's talk about GPT: A crash course in Generative AI for researchers par Steven Van Vaerenbergh
Let's talk about GPT: A crash course in Generative AI for researchersLet's talk about GPT: A crash course in Generative AI for researchers
Let's talk about GPT: A crash course in Generative AI for researchers
Generative AI Art - The Dark Side par Abhinav Gupta
Generative AI Art - The Dark SideGenerative AI Art - The Dark Side
Generative AI Art - The Dark Side
Abhinav Gupta266 vues
USE OF GENERATIVE AI IN THE FIELD OF PUBLIC RELATIONS.pdf par AnushkaRoyBardhan1
USE OF GENERATIVE AI IN THE FIELD OF PUBLIC RELATIONS.pdfUSE OF GENERATIVE AI IN THE FIELD OF PUBLIC RELATIONS.pdf
USE OF GENERATIVE AI IN THE FIELD OF PUBLIC RELATIONS.pdf
Understanding generative AI models A comprehensive overview.pdf par StephenAmell4
Understanding generative AI models A comprehensive overview.pdfUnderstanding generative AI models A comprehensive overview.pdf
Understanding generative AI models A comprehensive overview.pdf
StephenAmell4455 vues

Similaire à Leveraging Generative AI & Best practices

Scaling Training Data for AI Applications par
Scaling Training Data for AI ApplicationsScaling Training Data for AI Applications
Scaling Training Data for AI ApplicationsApplause
129 vues26 diapositives
Cloudera Fast Forward Labs: Accelerate machine learning par
Cloudera Fast Forward Labs: Accelerate machine learningCloudera Fast Forward Labs: Accelerate machine learning
Cloudera Fast Forward Labs: Accelerate machine learningCloudera, Inc.
1.6K vues59 diapositives
Putting data science in your business a first utility feedback par
Putting data science in your business a first utility feedbackPutting data science in your business a first utility feedback
Putting data science in your business a first utility feedbackPeculium Crypto
520 vues28 diapositives
Ai and Design: When, Why and How? - Morgenbooster par
Ai and Design: When, Why and How? - MorgenboosterAi and Design: When, Why and How? - Morgenbooster
Ai and Design: When, Why and How? - Morgenbooster1508 A/S
154 vues66 diapositives
Technology and Innovation - Introduction par
Technology and Innovation - IntroductionTechnology and Innovation - Introduction
Technology and Innovation - IntroductionLee Schlenker
342 vues23 diapositives
AI Orange Belt - Session 3 par
AI Orange Belt - Session 3AI Orange Belt - Session 3
AI Orange Belt - Session 3AI Black Belt
1.3K vues115 diapositives

Similaire à Leveraging Generative AI & Best practices(20)

Scaling Training Data for AI Applications par Applause
Scaling Training Data for AI ApplicationsScaling Training Data for AI Applications
Scaling Training Data for AI Applications
Applause129 vues
Cloudera Fast Forward Labs: Accelerate machine learning par Cloudera, Inc.
Cloudera Fast Forward Labs: Accelerate machine learningCloudera Fast Forward Labs: Accelerate machine learning
Cloudera Fast Forward Labs: Accelerate machine learning
Cloudera, Inc.1.6K vues
Putting data science in your business a first utility feedback par Peculium Crypto
Putting data science in your business a first utility feedbackPutting data science in your business a first utility feedback
Putting data science in your business a first utility feedback
Peculium Crypto520 vues
Ai and Design: When, Why and How? - Morgenbooster par 1508 A/S
Ai and Design: When, Why and How? - MorgenboosterAi and Design: When, Why and How? - Morgenbooster
Ai and Design: When, Why and How? - Morgenbooster
1508 A/S154 vues
Technology and Innovation - Introduction par Lee Schlenker
Technology and Innovation - IntroductionTechnology and Innovation - Introduction
Technology and Innovation - Introduction
Lee Schlenker342 vues
AI Orange Belt - Session 3 par AI Black Belt
AI Orange Belt - Session 3AI Orange Belt - Session 3
AI Orange Belt - Session 3
AI Black Belt1.3K vues
An AI Maturity Roadmap for Becoming a Data-Driven Organization par David Solomon
An AI Maturity Roadmap for Becoming a Data-Driven OrganizationAn AI Maturity Roadmap for Becoming a Data-Driven Organization
An AI Maturity Roadmap for Becoming a Data-Driven Organization
David Solomon911 vues
INFRAGARD 2014: Back to basics security par Joel Cardella
INFRAGARD 2014: Back to basics securityINFRAGARD 2014: Back to basics security
INFRAGARD 2014: Back to basics security
Joel Cardella1.5K vues
Operationalizing Machine Learning in the Enterprise par mark madsen
Operationalizing Machine Learning in the EnterpriseOperationalizing Machine Learning in the Enterprise
Operationalizing Machine Learning in the Enterprise
mark madsen756 vues
Transform Banking with Big Data and Automated Machine Learning 9.12.17 par Cloudera, Inc.
Transform Banking with Big Data and Automated Machine Learning 9.12.17Transform Banking with Big Data and Automated Machine Learning 9.12.17
Transform Banking with Big Data and Automated Machine Learning 9.12.17
Cloudera, Inc.2.4K vues
5 Questions To Ask Before Getting Started With Data Annotation par Innodata, Inc
5 Questions To Ask Before Getting Started With Data Annotation5 Questions To Ask Before Getting Started With Data Annotation
5 Questions To Ask Before Getting Started With Data Annotation
Innodata, Inc26.1K vues
How to classify documents automatically using NLP par Skyl.ai
How to classify documents automatically using NLPHow to classify documents automatically using NLP
How to classify documents automatically using NLP
Skyl.ai76 vues
Data and analytic strategies for developing ethical it par Hyoun Park
Data and analytic strategies for developing ethical itData and analytic strategies for developing ethical it
Data and analytic strategies for developing ethical it
Hyoun Park231 vues
Why Everything You Know About bigdata Is A Lie par Sunil Ranka
Why Everything You Know About bigdata Is A LieWhy Everything You Know About bigdata Is A Lie
Why Everything You Know About bigdata Is A Lie
Sunil Ranka321 vues
SDD2017 - 03 Abed Ajraou - putting data science in your business a first uti... par Dario Mangano
SDD2017 - 03 Abed Ajraou  - putting data science in your business a first uti...SDD2017 - 03 Abed Ajraou  - putting data science in your business a first uti...
SDD2017 - 03 Abed Ajraou - putting data science in your business a first uti...
Dario Mangano238 vues

Plus de DianaGray10

Business Analyst Series 2023 - Week 4 Session 7 par
Business Analyst Series 2023 -  Week 4 Session 7Business Analyst Series 2023 -  Week 4 Session 7
Business Analyst Series 2023 - Week 4 Session 7DianaGray10
80 vues31 diapositives
Business Analyst Series 2023 - Week 3 Session 5 par
Business Analyst Series 2023 -  Week 3 Session 5Business Analyst Series 2023 -  Week 3 Session 5
Business Analyst Series 2023 - Week 3 Session 5DianaGray10
369 vues20 diapositives
Business Analyst Series 2023 - Week 2 Session 3 par
Business Analyst Series 2023 -  Week 2 Session 3Business Analyst Series 2023 -  Week 2 Session 3
Business Analyst Series 2023 - Week 2 Session 3DianaGray10
379 vues22 diapositives
Business Analyst Series 2023 - Week 1 Session 1 par
Business Analyst Series 2023 -  Week 1 Session 1Business Analyst Series 2023 -  Week 1 Session 1
Business Analyst Series 2023 - Week 1 Session 1DianaGray10
381 vues32 diapositives
Business Analyst Series 2023 - Week 1 Session 2 par
Business Analyst Series 2023 -  Week 1 Session 2Business Analyst Series 2023 -  Week 1 Session 2
Business Analyst Series 2023 - Week 1 Session 2DianaGray10
459 vues27 diapositives
UiPath Certified Professional Certification for Specialized AI.pptx par
UiPath Certified Professional Certification for Specialized AI.pptxUiPath Certified Professional Certification for Specialized AI.pptx
UiPath Certified Professional Certification for Specialized AI.pptxDianaGray10
169 vues15 diapositives

Plus de DianaGray10(20)

Business Analyst Series 2023 - Week 4 Session 7 par DianaGray10
Business Analyst Series 2023 -  Week 4 Session 7Business Analyst Series 2023 -  Week 4 Session 7
Business Analyst Series 2023 - Week 4 Session 7
DianaGray1080 vues
Business Analyst Series 2023 - Week 3 Session 5 par DianaGray10
Business Analyst Series 2023 -  Week 3 Session 5Business Analyst Series 2023 -  Week 3 Session 5
Business Analyst Series 2023 - Week 3 Session 5
DianaGray10369 vues
Business Analyst Series 2023 - Week 2 Session 3 par DianaGray10
Business Analyst Series 2023 -  Week 2 Session 3Business Analyst Series 2023 -  Week 2 Session 3
Business Analyst Series 2023 - Week 2 Session 3
DianaGray10379 vues
Business Analyst Series 2023 - Week 1 Session 1 par DianaGray10
Business Analyst Series 2023 -  Week 1 Session 1Business Analyst Series 2023 -  Week 1 Session 1
Business Analyst Series 2023 - Week 1 Session 1
DianaGray10381 vues
Business Analyst Series 2023 - Week 1 Session 2 par DianaGray10
Business Analyst Series 2023 -  Week 1 Session 2Business Analyst Series 2023 -  Week 1 Session 2
Business Analyst Series 2023 - Week 1 Session 2
DianaGray10459 vues
UiPath Certified Professional Certification for Specialized AI.pptx par DianaGray10
UiPath Certified Professional Certification for Specialized AI.pptxUiPath Certified Professional Certification for Specialized AI.pptx
UiPath Certified Professional Certification for Specialized AI.pptx
DianaGray10169 vues
Business Analyst Series 2023 - Week 1 Session 1 par DianaGray10
Business Analyst Series 2023 -  Week 1 Session 1Business Analyst Series 2023 -  Week 1 Session 1
Business Analyst Series 2023 - Week 1 Session 1
DianaGray10456 vues
Introduction to RPA and Document Understanding par DianaGray10
Introduction to RPA and Document UnderstandingIntroduction to RPA and Document Understanding
Introduction to RPA and Document Understanding
DianaGray1065 vues
Navigating the Future: UiPath’s Latest Certifications Unveiled par DianaGray10
Navigating the Future: UiPath’s Latest Certifications UnveiledNavigating the Future: UiPath’s Latest Certifications Unveiled
Navigating the Future: UiPath’s Latest Certifications Unveiled
DianaGray1077 vues
Connector Corner: How Jira-and Open AI-support service issues in multiple la... par DianaGray10
Connector Corner: How Jira-and Open AI-support service issues in multiple  la...Connector Corner: How Jira-and Open AI-support service issues in multiple  la...
Connector Corner: How Jira-and Open AI-support service issues in multiple la...
DianaGray1098 vues
Secure Your Environment with UiPath and CyberArk Technologies par DianaGray10
Secure Your Environment with UiPath and CyberArk TechnologiesSecure Your Environment with UiPath and CyberArk Technologies
Secure Your Environment with UiPath and CyberArk Technologies
DianaGray1040 vues
Explore the Possibilities of Document Understanding and Generative AI par DianaGray10
Explore the Possibilities of Document Understanding and  Generative AIExplore the Possibilities of Document Understanding and  Generative AI
Explore the Possibilities of Document Understanding and Generative AI
DianaGray1098 vues
Connector Corner: Streamline onboarding by combining Workday Events with Azur... par DianaGray10
Connector Corner: Streamline onboarding by combining Workday Events with Azur...Connector Corner: Streamline onboarding by combining Workday Events with Azur...
Connector Corner: Streamline onboarding by combining Workday Events with Azur...
DianaGray1092 vues
Mastering Automation Quality: Exploring UiPath's Test Suite for Seamless Test... par DianaGray10
Mastering Automation Quality: Exploring UiPath's Test Suite for Seamless Test...Mastering Automation Quality: Exploring UiPath's Test Suite for Seamless Test...
Mastering Automation Quality: Exploring UiPath's Test Suite for Seamless Test...
DianaGray1078 vues
UiPath Tips and Techniques for Debugging - Session 3 par DianaGray10
UiPath Tips and Techniques for Debugging - Session 3UiPath Tips and Techniques for Debugging - Session 3
UiPath Tips and Techniques for Debugging - Session 3
DianaGray1097 vues
Document Understanding as Cloud APIs and Generative AI Pre-labeling Extractio... par DianaGray10
Document Understanding as Cloud APIs and Generative AI Pre-labeling Extractio...Document Understanding as Cloud APIs and Generative AI Pre-labeling Extractio...
Document Understanding as Cloud APIs and Generative AI Pre-labeling Extractio...
DianaGray10369 vues
UiPath Tips and Techniques for Error Handling - Session 2 par DianaGray10
UiPath Tips and Techniques for Error Handling - Session 2UiPath Tips and Techniques for Error Handling - Session 2
UiPath Tips and Techniques for Error Handling - Session 2
DianaGray1053 vues
UiPath Tips and Techniques for Exception Planning - Session 1 par DianaGray10
UiPath Tips and Techniques for Exception Planning - Session 1UiPath Tips and Techniques for Exception Planning - Session 1
UiPath Tips and Techniques for Exception Planning - Session 1
DianaGray1073 vues
UiPath Tips and Techniques for Exception Planning - Session 1 par DianaGray10
UiPath Tips and Techniques for Exception Planning - Session 1UiPath Tips and Techniques for Exception Planning - Session 1
UiPath Tips and Techniques for Exception Planning - Session 1
DianaGray1013 vues
UiPath Connector Corner: How Microsoft Teams Powers Automation Collaboration par DianaGray10
UiPath Connector Corner:  How Microsoft Teams Powers Automation CollaborationUiPath Connector Corner:  How Microsoft Teams Powers Automation Collaboration
UiPath Connector Corner: How Microsoft Teams Powers Automation Collaboration
DianaGray10104 vues

Dernier

【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院 par
【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院
【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院IttrainingIttraining
80 vues8 diapositives
The Research Portal of Catalonia: Growing more (information) & more (services) par
The Research Portal of Catalonia: Growing more (information) & more (services)The Research Portal of Catalonia: Growing more (information) & more (services)
The Research Portal of Catalonia: Growing more (information) & more (services)CSUC - Consorci de Serveis Universitaris de Catalunya
136 vues25 diapositives
Scaling Knowledge Graph Architectures with AI par
Scaling Knowledge Graph Architectures with AIScaling Knowledge Graph Architectures with AI
Scaling Knowledge Graph Architectures with AIEnterprise Knowledge
53 vues15 diapositives
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N... par
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...James Anderson
133 vues32 diapositives
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit... par
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...ShapeBlue
57 vues25 diapositives
Keynote Talk: Open Source is Not Dead - Charles Schulz - Vates par
Keynote Talk: Open Source is Not Dead - Charles Schulz - VatesKeynote Talk: Open Source is Not Dead - Charles Schulz - Vates
Keynote Talk: Open Source is Not Dead - Charles Schulz - VatesShapeBlue
119 vues15 diapositives

Dernier(20)

【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院 par IttrainingIttraining
【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院
【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N... par James Anderson
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...
James Anderson133 vues
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit... par ShapeBlue
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...
ShapeBlue57 vues
Keynote Talk: Open Source is Not Dead - Charles Schulz - Vates par ShapeBlue
Keynote Talk: Open Source is Not Dead - Charles Schulz - VatesKeynote Talk: Open Source is Not Dead - Charles Schulz - Vates
Keynote Talk: Open Source is Not Dead - Charles Schulz - Vates
ShapeBlue119 vues
Automating a World-Class Technology Conference; Behind the Scenes of CiscoLive par Network Automation Forum
Automating a World-Class Technology Conference; Behind the Scenes of CiscoLiveAutomating a World-Class Technology Conference; Behind the Scenes of CiscoLive
Automating a World-Class Technology Conference; Behind the Scenes of CiscoLive
CloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlue par ShapeBlue
CloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlueCloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlue
CloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlue
ShapeBlue46 vues
Five Things You SHOULD Know About Postman par Postman
Five Things You SHOULD Know About PostmanFive Things You SHOULD Know About Postman
Five Things You SHOULD Know About Postman
Postman40 vues
CloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlue par ShapeBlue
CloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlueCloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlue
CloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlue
ShapeBlue46 vues
NTGapps NTG LowCode Platform par Mustafa Kuğu
NTGapps NTG LowCode Platform NTGapps NTG LowCode Platform
NTGapps NTG LowCode Platform
Mustafa Kuğu141 vues
Don’t Make A Human Do A Robot’s Job! : 6 Reasons Why AI Will Save Us & Not De... par Moses Kemibaro
Don’t Make A Human Do A Robot’s Job! : 6 Reasons Why AI Will Save Us & Not De...Don’t Make A Human Do A Robot’s Job! : 6 Reasons Why AI Will Save Us & Not De...
Don’t Make A Human Do A Robot’s Job! : 6 Reasons Why AI Will Save Us & Not De...
Moses Kemibaro29 vues
CloudStack and GitOps at Enterprise Scale - Alex Dometrius, Rene Glover - AT&T par ShapeBlue
CloudStack and GitOps at Enterprise Scale - Alex Dometrius, Rene Glover - AT&TCloudStack and GitOps at Enterprise Scale - Alex Dometrius, Rene Glover - AT&T
CloudStack and GitOps at Enterprise Scale - Alex Dometrius, Rene Glover - AT&T
ShapeBlue56 vues
Data Integrity for Banking and Financial Services par Precisely
Data Integrity for Banking and Financial ServicesData Integrity for Banking and Financial Services
Data Integrity for Banking and Financial Services
Precisely56 vues
PharoJS - Zürich Smalltalk Group Meetup November 2023 par Noury Bouraqadi
PharoJS - Zürich Smalltalk Group Meetup November 2023PharoJS - Zürich Smalltalk Group Meetup November 2023
PharoJS - Zürich Smalltalk Group Meetup November 2023
Noury Bouraqadi141 vues
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P... par ShapeBlue
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...
ShapeBlue82 vues
Backroll, News and Demo - Pierre Charton, Matthias Dhellin, Ousmane Diarra - ... par ShapeBlue
Backroll, News and Demo - Pierre Charton, Matthias Dhellin, Ousmane Diarra - ...Backroll, News and Demo - Pierre Charton, Matthias Dhellin, Ousmane Diarra - ...
Backroll, News and Demo - Pierre Charton, Matthias Dhellin, Ousmane Diarra - ...
ShapeBlue83 vues
"Surviving highload with Node.js", Andrii Shumada par Fwdays
"Surviving highload with Node.js", Andrii Shumada "Surviving highload with Node.js", Andrii Shumada
"Surviving highload with Node.js", Andrii Shumada
Fwdays40 vues
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT par ShapeBlue
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBITUpdates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT
ShapeBlue91 vues

Leveraging Generative AI & Best practices

  • 1. Leveraging Generative AI Ashling Partners | Solutions Engineering | Alp Uguray, 4x UiPath MVP
  • 2. 2 Senior Solutions Engineer at Ashling Partners 4x UiPath MVP Award Host & Creator at Masters of Automation Podcast (https://themasters.ai) Alp Uguray Introductions
  • 3. Innovation Ambition Matrix HOW TO WIN WHERE TO PLAY TRANSFORMATIONAL Large market opportunity identified but very different from what we are doing today. ADJACENT Not doing today, but plugs right into what we are doing today CORE Already doing it today Develop New Products & Assets Add incremental Products & Assets Use Existing Products & Assets Serve existing Markets & Customers Enter Adjacent Markets Serve Adjacent Customers Create New Market Target New Customers
  • 4. 4
  • 5. 5 Good ones (Utopic Use) • Leverages AI versus. Manual execution productivity gains • Augmentation in task execution as HITL suggestions and recommendations Not so good ones (Most likely) • Job Displacement / Re-write • Digital Misuse • Digital Divide • Vulnerability increase with cyberattacks Worst ones (Cautious view) • Data Privacy • Fake Content and IP Law • Failure of Regulations • LLMs dominate the communication lines - Don’t know who you speak and widespread adoption of personalized Face, Voice and Text Importance of Scenario Planning Driven by productivity gains and improved Customer and Employee Experiences, Conversational AI dominance depends on a few different outcomes based on its adoption
  • 6. 6 Focus on realistic applications that can complement existing business capabilities. • Prioritize applications based on ease of implementation and risk level, gradually moving towards more complex and valuable ones. An example of a key application is using generative AI for knowledge management, which can provide immediate value across various business functions Do not have a perfectionist attitude towards the development of AI applications, which could trap you in the proof-of-concept phase without ever delivering value. • An iterative product development approach where applications are developed to solve specific customer or employee problems and are then continuously adjusted based on feedback until they're ready to be scaled. This ensures that the efforts have purpose and contribute towards transforming the industry standards​ The importance of ensuring that AI adoption doesn't compromise the organization's data and intellectual property security, customer data security, brand credibility, and legal protections. • Collaboration between leaders from operations, technology and data teams, and the legal department to create guardrails that empower the organization without hindering it. Some Guiding Principles in Adoption
  • 7. What’s prompt engineering? Prompt engineering is the ‘art’ of optimizing natural language for a LLM. Effective prompts provide the relevant context and detail to a LLM, therefore improving the accuracy and relevance of the response. The quality of prompts directly affects the output of the model. Effective prompts help the model understand your request and generate appropriate responses, in complex or ambiguous scenarios. Tips / Tricks – • Zero-shot Learning: never seen your data, but makes inferences based on understanding • CoT (chain-of-thought) reasoning, ‘break it down, step-by-step’ • Providing relevant context, ‘I am’ or ‘you are’ • First, do ‘xyz’, then do ‘xyz’, finally…
  • 8. 8 Zero-shot learning This is a problem set up in machine learning where the model is asked to classify data accurately it has never seen before during training. In other words, the model is expected to infer classes that were not part of its training data. The model typically leverages high- level abstractions and understandings learned from the training data to make accurate predictions on the unseen classes. Zero-shot learning is especially important in settings where it is costly or time-consuming to collect large labeled datasets for every possible class. Few-shot learning Few-shot learning refers to the concept where a machine learning model is able to generalize well from a small number of examples – often just one or two, hence the term "one-shot" or "two-shot" learning. In a traditional machine learning context, models are often trained on large amounts of data, but in few-shot learning, the idea is to design models that can extract useful information from a small number of examples and make accurate predictions. This is similar to how humans can often learn concepts from just a few examples. Shot Learnings
  • 9. Some considerations Data privacy and security: • Avoid using real customer data or any personally identifiable information (PII). • Use anonymized or synthetic data sets whenever possible. • Ensure data storage and transfer follow best practices and comply with relevant regulations, such as GDPR or HIPAA. “Hallucinations” - ChatGPT can make stuff up. • Be aware of potential biases in data sets and algorithms, which could lead to unfair or discriminatory outcomes. • Use techniques such as data pre-processing or algorithmic adjustments to minimize the impact of biases. Responsible use of AI: • Ensure that your solution aligns with ethical principles and responsible AI guidelines. • Avoid applications that could be harmful, discriminatory, or promote misinformation.
  • 11. 11 RLHF Reinforcement learning from human feedback further aligns models. (Diagram from OpenAI ChatGPT announcement.)
  • 12. 12 Prompting with the “format trick” “Use this format:” is all you need. © 2 0 2 3 S c a l e I n c .
  • 13. 13 Specifying tasks using code prompts Prompting through partial code. © 2 0 2 3 S c a l e I n c .
  • 14. 14 Specifying tasks using code prompts Prompting with imaginary variables. © 2 0 2 3 S c a l e I n c .
  • 15. 15 Using an external interpreter to overcome model limitations in conversational Q&A. “You are GPT-3” © 2 0 2 3 S c a l e I n c .
  • 16. 16 Chain-of-thought prompting Figure 1 from Jason Wei et al. (2022). © 2 0 2 3 S c a l e I n c .
  • 17. 17 Zero-shot chain-of-thought Figure 1 from Takeshi Kojima et al. (2022). © 2 0 2 3 S c a l e I n c .
  • 18. 18 Zero-shot chain-of-thought Figure 2 from Takeshi Kojima et al. (2022). © 2 0 2 3 S c a l e I n c .
  • 19. 19 Zero-shot chain-of-thought Figure 2 from Takeshi Kojima et al. (2022). © 2 0 2 3 S c a l e I n c .
  • 20. 20 Self-consistency and consensus Figure 1 from Xuezhi Wang et al. (2022). © 2 0 2 3 S c a l e I n c .