Artificial Intelligence Day 6 Slides for your Reference Happy Learning

Microsoft Azure AI Fundamentals:
Generative AI
Subtitle or speaker name
Sreya E P

Agenda
•Fundamentals of Generative AI
•Language models
•Copilots and AI Agents
•Considerations for prompts
•Extending and Developing copilots like Agents
•Introduction to Azure AI Foundry
•Responsible Generative AI
•Demo
•Conclusion

Introduction
Generative AI is a fascinating subfield of artificial intelligence focused on
creating new content, such as text, images, music, and more, based on
the patterns and data it has learned.
How Generative AI Works
1.Training:
1. The model is trained on a large dataset of examples (e.g., text,
images).
2. It learns patterns and features within the data.
2.Generation:
1. Once trained, the model can generate new content by sampling
from the learned distribution.
2. For instance, a text generation model can predict the next word
in a sentence to create paragraphs of coherent text.
3.Evaluation:
1. The generated content is evaluated for quality and relevance.
2. In GANs, this is done using a discriminator network that
distinguishes between real and generated data.

What is generative AI?
• Generative AI describes a category of capabilities within AI that
create original content. People typically interact with
generative AI that has been built into chat applications
• . One popular example of such an application is
Microsoft Copilot, an AI-powered productivity tool designed to
enhance your work experience by providing real-time
intelligence and assistance.
• Generative AI applications take in natural language input, and
return appropriate responses in a variety of formats such as
natural language, images, code, and more.

What are language models?
Transformer models
Transformer models are trained with large volumes
of text, enabling them to represent the semantic
relationships between words and use those
relationships to determine probable sequences of
text that make sense. Transformer models with a
large enough vocabulary are capable of generating
language responses that are tough to distinguish
from human responses.
Transformer model architecture consists of two
components, or blocks:
•An encoder block that creates semantic
representations of the training vocabulary.
•A decoder block that generates new language
sequences.

Copilot and AI agents
• Microsoft Copilot is a generative AI based
assistant that is integrated into a wide range of
Microsoft applications and user experiences.
• It is based on an open architecture that enables
third-party developers to extend the Microsoft
Copilot user experience.
• Additionally, third-party developers can create
their own copilot-like agents using the same
open architecture.

Considerations for prompts
The quality of responses from generative AI assistants not only
depends on the language model used, but on the types of
prompts users provide.
Consider the following ways you can improve the response a
generative AI assistant provides:
1.Start with a specific goal for what you want the assistant to do
2.Provide a source to ground the response in a specific scope of
information
3.Add context to maximize response appropriateness and
relevance
4.Set clear expectations for the response
5.Iterate based on previous prompts and responses to refine the
result

Extending and developing copilot-like agents
Copilot Studio
Copilot Studio is designed to work well
for low-code development scenarios in
which technically proficient business
users or developers can create
conversational AI experiences. The
resulting agent is a fully managed SaaS
(software as a service) solution, hosted
in your Microsoft 365 environment and
delivered through chat channels like
Microsoft Teams.

Extending and developing copilot-like agents
Azure AI Foundry
Azure AI Foundry is a PaaS (platform as
a service) platform for developers that
gives you full control over the
language models you want to use,
including the capability to fine-tune
the models with your own data. You
can define prompt flows, orchestrate
conversation flow, integrate your own
data augmentation and prompt
engineering logic, and you can deploy
the resulting copilot service in the
cloud and consume it from custom-
developed apps and services. Learn
more about Azure AI Foundry here.

Introduction to Azure AI Foundry

Introduction
The Azure AI Foundry portal brings together
capabilities to provide a single, centralized
workspace within which developers can
collaborate with data scientists and others to
build AI solutions. Azure AI Foundry is
designed for developers to:
•Build generative AI applications on an
enterprise-grade platform.
•Explore, build, test, and deploy using
cutting-edge AI tools and ML models,
grounded in responsible AI practices.
•Collaborate with a team for the full life-cycle
of application development.

What can I do with Azure AI Foundry?
Azure AI Foundry enables teams to collaborate efficiently and effectively on AI projects, such as developing generative AI
apps that use language models. Tasks you can accomplish with the Azure AI Foundry portal include:
•Deploying models from the model catalog to real-time inferencing endpoints for client applications to consume.
•Deploying and testing generative AI models in an Azure OpenAI service.
•Integrating data from custom data sources to support a retrieval augmented generation (RAG) approach to prompt
engineering for generative AI models.
•Using prompt flow to define workflows that integrate models, prompts, and custom processing.
•Integrating content safety filters into a generative AI solution to mitigate potential harms.
•Extending a generative AI solution with multiple AI capabilities using Azure AI services.

When to use Azure AI Foundry
•Create and manage AI projects:
•Develop generative AI applications
•Explore available AI models
•Leverage Retrieval Augmented Generation (RAG)
•Monitor and evaluate AI models
•Integrate with Azure services
•Build responsibly

Introduction
• Generative AI is one of the most powerful advances in
technology ever. It enables developers to build applications that
consume machine learning models trained with a large volume
of data from across the Internet to generate new content that
can be indistinguishable from content created by a human.
• With such powerful capabilities, generative AI brings with it
some dangers; and requires that data scientists, developers, and
others involved in creating generative AI solutions adopt a
responsible approach that identifies, measures, and mitigates
risks.

Plan a responsible generative AI solution
The Microsoft guidance for responsible generative AI is designed to
be practical and actionable. It defines a four stage process to
develop and implement a plan for responsible AI when using
generative models. The four stages in the process are:
1.Identify potential harms that are relevant to your planned
solution.
2.Measure the presence of these harms in the outputs generated by
your solution.
3.Mitigate the harms at multiple layers in your solution to minimize
their presence and impact, and ensure transparent communication
about potential risks to users.
4.Operate the solution responsibly by defining and following a
deployment and operational readiness plan.

Identify potential harms
The first stage in a responsible generative
AI process is to identify the potential harms
that could affect your planned solution.
There are four steps in this stage, as shown
here:
1.Identify potential harms
2.Prioritize identified harms
3.Test and verify the prioritized harms
4.Document and share the verified harms

Measure potential harms
A generalized approach to measuring a
system for potential harms consists of three
steps:
1.Prepare a diverse selection of input
prompts that are likely to result in each
potential harm that you have documented
for the system
2.Submit the prompts to the system and
retrieve the generated output.
3.Apply pre-defined criteria to evaluate the
output and categorize it according to the
level of potential harm it contains.

Mitigate potential harms
Mitigation of potential harms in a
generative AI solution involves a layered
approach, in which mitigation techniques
can be applied at each of four layers, as
shown here:
1.Model
2.Safety System
3.Metaprompt and grounding
4.User experience

Operate a responsible generative AI solution
• Complete prerelease reviews-Before releasing a generative AI solution, identify the various compliance requirements
in your organization and industry and ensure the appropriate teams are given the opportunity to review the system and
its documentation. Common compliance reviews include: Legal, Privacy, Security and Accessibility
• Release and operate the solution-Devise a phased delivery plan, Create an incident response plan, Create a rollback
plan Implement the capability to immediately block harmful system responses, Implement a capability to block specific
users, applications, or client IP addresses in the event of system misuse, Implement a way for users to provide feedback
and report issues, Track telemetry data.
• Utilize Azure AI Content Safety

Artificial Intelligence Day 6 Slides for your Reference Happy Learning

More Related Content

Similar to Artificial Intelligence Day 6 Slides for your Reference Happy Learning (20)

Recently uploaded (20)

Artificial Intelligence Day 6 Slides for your Reference Happy Learning

Editor's Notes