AI-100: Designing and Implementing an Azure AI
Solution

Analyze solution requirements (25-30%)


Recommend Azure Cognitive Services APIs to meet business requirements
 select the processing architecture for a solution
 select the appropriate data processing technologies
 select the appropriate AI models and services
 identify components and technologies required to connect service endpoints
 identify automation requirements
Map security requirements to tools, technologies, and processes
 identify processes and regulations needed to conform with data privacy, protection, and
regulatory requirements
 identify which users and groups have access to information and interfaces
 identify appropriate tools for a solution
 identify auditing requirements
Select the software, services, and storage required to support a solution
 identify appropriate services and tools for a solution
 identify integration points with other Microsoft services
 identify storage required to store logging, bot state data, and Azure Cognitive Services
output


Design AI solutions (40-45%)


Design solutions that include one or more pipelines
 define an AI application workflow process
 design a strategy for ingest and egress data
 design the integration point between multiple workflows and pipelines
 design pipelines that use AI apps
 design pipelines that call Azure Machine Learning models
 select an AI solution that meet cost constraints
Design solutions that uses Cognitive Services
 design solutions that use vision, speech, language, knowledge, search, and anomaly
detection APIs
Design solutions that implement the Microsoft Bot Framework
 integrate bots and AI solutions
 design bot services that use Language Understanding (LUIS)
 design bots that integrate with channels
 integrate bots with Azure app services and Azure Application Insights
Design the compute infrastructure to support a solution
 identify whether to create a GPU, FPGA, or CPU-based solution
 identify whether to use a cloud-based, on-premises, or hybrid compute infrastructure
 select a compute solution that meets cost constraints
Design for data governance, compliance, integrity, and security
 define how users and applications will authenticate to AI services
 design a content moderation strategy for data usage within an AI solution
 ensure that data adheres to compliance requirements defined by your organization
 ensure appropriate governance of data
 design strategies to ensure that the solution meets data privacy regulations and industry
standards


Implement and monitor AI solutions (25-30%)


Implement an AI workflow
 develop AI pipelines
 manage the flow of data through the solution components
 implement data logging processes
 define and construct interfaces for custom AI services
 create solution endpoints
 develop streaming solutions
Integrate AI services and solution components
 configure prerequisite components and input datasets to allow the consumption of
Azure Cognitive Services APIs
 configure integration with Azure Cognitive Services
 configure prerequisite components to allow connectivity to the Microsoft Bot Framework
 implement Azure Cognitive Search in a solution
Monitor and evaluate the AI environment
 identify the differences between KPIs, reported metrics, and root causes of the
differences
 identify the differences between expected and actual workflow throughput
 maintain an AI solution for continuous improvement
 monitor AI components for availability
 recommend changes to an AI solution based on performance data
The exam guide below shows the changes that were implemented on May 20, 2020.


Audience Profile


Candidates for this exam should have subject matter expertise using cognitive services, machine
learning, and knowledge mining to architect and implement Microsoft AI solutions involving
natural language processing, speech, computer vision, and conversational AI.
Responsibilities for an Azure AI Engineer include analyzing requirements for AI solutions,
recommending the appropriate tools and technologies, and designing and implementing AI
solutions that meet scalability and performance requirements.
Azure AI Engineers translate the vision from solution architects and work with data scientists,
data engineers, IoT specialists, and software developers to build complete end-to-end solutions.
A candidate for this exam should have knowledge and experience designing and implementing
AI apps and agents that use Microsoft Azure Cognitive Services, Azure Bot Service, Azure
Cognitive Search, and data storage in Azure. In addition, a candidate should be able to
recommend solutions that use open source technologies, understand the components that
make up the Azure AI portfolio and the available data storage options, and understand when a
custom API should be developed to meet specific requirements.


Skills Measured


NOTE: The bullets that appear below each of the skills measured are intended to illustrate how
we are assessing that skill. This list is not definitive or exhaustive.
NOTE: In most cases, exams do NOT cover preview features, and some features will only be
added to an exam when they are GA (General Availability).


Analyze solution requirements (25-30%)


Recommend Azure Cognitive Services APIs to meet business requirements
 select the processing architecture for a solution
 select the appropriate data processing technologies
 select the appropriate AI models and services
 identify components and technologies required to connect service endpoints
 identify automation requirements
Map security requirements to tools, technologies, and processes
 identify processes and regulations needed to conform with data privacy, protection, and
regulatory requirements
 identify which users and groups have access to information and interfaces
 identify appropriate tools for a solution
 identify auditing requirements
Select the software, services, and storage required to support a solution
 identify appropriate services and tools for a solution
 identify integration points with other Microsoft services
 identify storage required to store logging, bot state data, and Azure Cognitive Services
output


Design AI solutions (40-45%)

Design solutions that include one or more pipelines
 define an AI application workflow process
 design a strategy for ingest and egress data
 design the integration point between multiple workflows and pipelines
 design pipelines that use AI apps
 design pipelines that call Azure Machine Learning models
 select an AI solution that meet cost constraints
Design solutions that uses Cognitive Services
 design solutions that use vision, speech, language, knowledge, search, and anomaly
detection APIs
Design solutions that implement the Microsoft Bot Framework
 integrate bots and AI solutions
 design bot services that use Language Understanding (LUIS)
 design bots that integrate with channels
 integrate bots with Azure app services and Azure Application Insights
Design the compute infrastructure to support a solution
 identify whether to create a GPU, FPGA, or CPU-based solution
 identify whether to use a cloud-based, on-premises, or hybrid compute infrastructure
 select a compute solution that meets cost constraints
Design for data governance, compliance, integrity, and security
 define how users and applications will authenticate to AI services
 design a content moderation strategy for data usage within an AI solution
 ensure that data adheres to compliance requirements defined by your organization
 ensure appropriate governance of data
 design strategies to ensure that the solution meets data privacy regulations and industry
standards


Implement and monitor AI solutions (25-30%)


Implement an AI workflow
 develop AI pipelines
 manage the flow of data through the solution components
 implement data logging processes
 define and construct interfaces for custom AI services
 create solution endpoints
 develop streaming solutions
Integrate AI services and solution components
 configure prerequisite components and input datasets to allow the consumption of
Azure Cognitive Services APIs
 configure integration with Azure Cognitive Services
 configure prerequisite components to allow connectivity to the Microsoft Bot Framework
 implement Azure Cognitive Search in a solution
Monitor and evaluate the AI environment
 identify the differences between KPIs, reported metrics, and root causes of the
differences
 identify the differences between expected and actual workflow throughput
 maintain an AI solution for continuous improvement
 monitor AI components for availability
 recommend changes to an AI solution based on performance data

Course Schedule

Scheduled DateLocationAvailableRegister
01/06/2023 - 15/06/2023BengaluruLive on-line / Classroom ClassesRegister

Course Details

Duration: 25 Hours
Exam Code: AI-100

Schedule

Date: 05/06/2023
– 15/06/2023
Location: Bengaluru
Available: VILT /ILT

Contact Us

Course Enquiry

Please submit the form, we'll be with you shortly.

Bootcamp Enquiry

Please submit the form, we'll be with you shortly.