We may earn an affiliate commission when you visit our partners.
Course image
Packt - Course Instructors

This course now features Coursera Coach!

A smarter way to learn with interactive, real-time conversations that help you test your knowledge, challenge assumptions, and deepen your understanding as you progress through the course.

Read more

This course now features Coursera Coach!

A smarter way to learn with interactive, real-time conversations that help you test your knowledge, challenge assumptions, and deepen your understanding as you progress through the course.

Unlock the full potential of AI-driven business solutions with the Semantic Kernel SDK. This course equips you with the knowledge to integrate Large Language Models (LLMs) and generative AI into your applications using Microsoft’s Semantic Kernel. You'll gain a deep understanding of how to create intelligent agents, build chat applications, and design plugins tailored to business needs.

The course begins with foundational concepts, including LLMs, generative AI, and the role of Semantic Kernel in modern applications. You’ll set up your development environment using tools like Visual Studio, VS Code, and Azure, preparing you for hands-on development. Next, you’ll dive into building your own Semantic Kernel, creating AI-powered chat applications, and configuring Azure OpenAI resources.

In the second half, you'll focus on extending the functionality of Semantic Kernel through built-in and custom plugins. You'll design career advisor tools, integrate personas, and manage prompts effectively. The course also covers native functions, their automation, and how to enhance interactions using function-prompt combinations.

This course is ideal for developers, software engineers, and tech-savvy business professionals interested in building AI-powered applications. A basic understanding of programming and familiarity with development environments like Visual Studio or Azure is recommended. The course is designed at an intermediate level.

Enroll now

What's inside

Syllabus

Introduction
In this module, we will introduce the Semantic Kernel SDK and establish its significance in the evolving landscape of AI integration. You'll get a clear understanding of what the course covers and how it empowers developers to build intelligent applications. This sets the stage for deeper technical exploration in subsequent modules.
Read more

Save this course

Create your own learning path. Save this course to your list so you can find it easily later.
Save

Career center

Learners who complete Semantic Kernel SDK for Intelligent Applications will develop knowledge and skills that may be useful to these careers:
Generative Artificial Intelligence Developer
A Generative Artificial Intelligence Developer focuses on creating applications and systems that leverage generative AI models to produce new content, solve complex problems, or enhance user interactions. This cutting-edge role demands both AI expertise and development prowess. This course is specifically designed for individuals looking to become a Generative Artificial Intelligence Developer. It immerses learners in the practical application of generative AI and Large Language Models using Microsoft’s Semantic Kernel SDK. Through hands-on modules, participants will learn to build intelligent agents, create AI-powered chat applications, and extend functionality with custom plugins. The course’s emphasis on configuring Azure OpenAI resources, designing career advisor tools, and enhancing interactions using function-prompt combinations directly aligns with the responsibilities of this role. By developing a full-stack AI-powered chat assistant, learners gain comprehensive skills in bringing generative AI solutions to life, from backend to user interface.
Chatbot Developer
A Chatbot Developer specializes in designing, building, and deploying conversational AI systems that can interact with users through text or voice. This role requires expertise in natural language processing and integration with backend services. This course is highly relevant for aspiring Chatbot Developers, as a significant portion is dedicated to building and enhancing AI-powered chat applications. Learners will gain hands-on experience creating a full-stack AI-powered chat assistant using the Semantic Kernel SDK, including implementing backend services, UI components, and managing chat history. The course covers crucial aspects like integrating Large Language Models and generative AI, designing custom plugins, managing prompts effectively, and leveraging techniques such as Retrieval Augmented Generation (RAG) to improve contextual accuracy. This comprehensive approach equips a Chatbot Developer with the practical skills to create sophisticated and intelligent conversational interfaces for myriad business needs.
Software Development Engineer Artificial Intelligence
A Software Development Engineer Artificial Intelligence specializes in building software applications that incorporate AI functionalities, often leveraging large language models and generative AI. This pivotal role combines traditional software development with advanced AI integration. This course is exceptionally well-suited for a Software Development Engineer Artificial Intelligence, as it provides specific training on using the Semantic Kernel SDK to develop intelligent applications. Learners will gain hands-on experience setting up development environments with Visual Studio and Azure, building AI-powered chat applications, and designing custom plugins tailored to business needs. The curriculum's focus on creating AI agents, managing prompts, and automating functions directly translates into the practical skills required to develop sophisticated AI-enhanced software. Furthermore, the development of a full-stack AI-powered chat assistant, including backend services and UI components, equips learners with the end-to-end knowledge valued in this field.
Artificial Intelligence Engineer
An Artificial Intelligence Engineer builds, deploys, and maintains AI systems, often integrating sophisticated models into production applications. This pivotal role requires a strong understanding of AI frameworks and deployment practices. This course directly addresses the core skills needed by an Artificial Intelligence Engineer by focusing on the practical application of Large Language Models and generative AI through the Semantic Kernel SDK. Learners will gain hands-on experience configuring development environments using Visual Studio and Azure, building intelligent applications, and creating AI-powered chat solutions. The ability to design custom plugins and manage prompts effectively, as taught in this course, is crucial for developing robust and adaptable AI solutions. Moreover, the course covers native functions and their automation, which is essential for developing interactive and intelligent agents. Someone aspiring to be an Artificial Intelligence Engineer will find this course helps establish a strong foundation for integrating cutting-edge AI technologies into real-world business solutions, preparing them for the demands of this dynamic field.
Machine Learning Engineer
A Machine Learning Engineer focuses on designing, building, and deploying machine learning models and systems. This often involves working with various AI paradigms, including generative AI and large language models, to create intelligent applications. This course directly supports the skillset required for a Machine Learning Engineer by providing a deep dive into the Semantic Kernel SDK, a powerful tool for integrating advanced AI capabilities into applications. Learners will work with foundational AI concepts, set up development environments with Azure, and create AI-powered chat applications. The emphasis on developing plugins, integrating personas, and managing prompts for effective AI interaction is highly relevant. Additionally, features like creating native functions and implementing Retrieval Augmented Generation (RAG) for contextual accuracy are practical skills for a Machine Learning Engineer. This course helps learners gain practical experience in building and deploying intelligent agents, which is a core responsibility of this role.
Application Developer AI Enhanced
An Application Developer AI Enhanced builds software applications that are significantly augmented by artificial intelligence capabilities, from basic integrations to complex intelligent agents. This role requires adapting traditional development skills to incorporate AI. This course is ideally suited for an Application Developer AI Enhanced, offering a direct pathway to integrating advanced AI into applications using the Semantic Kernel SDK. The curriculum provides hands-on experience in building intelligent agents, creating AI-powered chat applications, and designing custom plugins. Learners will set up development environments using Visual Studio and Azure, then dive into creating robust AI solutions. The course's focus on managing prompts, integrating native functions for automation, and developing full-stack AI assistants ensures that an Application Developer AI Enhanced gains the specific skills to embed sophisticated, generative AI features seamlessly into their applications, enhancing user experience and functionality.
AI Tools Developer
An AI Tools Developer creates and maintains software tools, SDKs, and platforms that empower other developers to build and integrate artificial intelligence capabilities into their applications. This role requires a deep understanding of AI frameworks and developer experience. This course is highly relevant for an AI Tools Developer, as it focuses entirely on the Semantic Kernel SDK, a prime example of such a tool. By deeply understanding how to use, extend, and apply the Semantic Kernel for building intelligent agents and chat applications, learners gain invaluable insights into effective SDK design and functionality from a user's perspective. The modules on creating custom plugins, native functions, and managing prompt systems directly mirror the kind of work an AI Tools Developer might do to enhance an SDK's capabilities or build supporting libraries. This comprehensive, hands-on experience provides a unique perspective on what makes an AI development tool effective and user-friendly.
Cloud Developer Azure
A Cloud Developer Azure specializes in building, deploying, and managing applications and services on Microsoft Azure. This role often involves leveraging Azure's extensive suite of services, including those for artificial intelligence. This course is highly relevant for a Cloud Developer Azure interested in integrating AI capabilities. It specifically guides learners through configuring their local environment with Azure integration, building necessary Azure resources, and configuring Azure OpenAI resources. The hands-on development of AI applications and a full-stack AI-powered chat assistant directly on Azure, utilizing its services, provides practical experience essential for this role. Understanding how to deploy and manage intelligent agents and generative AI solutions within the Azure ecosystem, as taught in this course, significantly enhances a Cloud Developer Azure’s ability to create cutting-edge, scalable cloud-native applications that leverage Microsoft's AI offerings.
Natural Language Processing Engineer
A Natural Language Processing Engineer develops systems that enable computers to understand, interpret, and generate human language. This typically involves working with language models, text analysis, and conversational AI. This course may be helpful for a Natural Language Processing Engineer by providing a practical framework for applying Large Language Models and generative AI, which are central to modern NLP. While the course focuses on application development rather than core NLP algorithm design, it deeply engages with how these models are integrated through the Semantic Kernel SDK to create intelligent applications and chat assistants. Learners will explore prompt management, persona integration, and the use of native functions to enhance language interactions. The course's module on Retrieval Augmented Generation (RAG) for improving contextual accuracy is particularly relevant for an NLP Engineer focused on building robust and understanding language systems.
Prompt Engineer
A Prompt Engineer specializes in crafting, refining, and optimizing prompts to guide large language models (LLMs) to perform specific tasks effectively and accurately. While often associated with textual inputs, this role also involves understanding model behavior and integration into larger systems. This course may be helpful for a Prompt Engineer by providing a comprehensive understanding of how LLMs and generative AI are integrated into applications using the Semantic Kernel SDK. Although the course delves into much broader application development, it explicitly covers managing prompts effectively and integrating personas to personalize responses. Learners will gain insights into how prompts interact within a larger intelligent agent framework and how they contribute to the functionality of AI-powered chat applications. This course could help a Prompt Engineer understand the architectural context of prompt usage and how their crafted prompts are utilized in real-world intelligent application development, offering a deeper technical perspective beyond just prompt creation.
Artificial Intelligence Consultant
An Artificial Intelligence Consultant advises businesses on how to strategically adopt, implement, and optimize AI technologies to solve specific challenges and drive innovation. This role requires a strong grasp of AI capabilities, technical feasibility, and business impact. This course may be useful for an Artificial Intelligence Consultant by providing a deep, practical understanding of how to implement cutting-edge AI solutions using the Semantic Kernel SDK. By gaining hands-on experience with Large Language Models and generative AI, building intelligent agents, and creating AI-powered chat applications, learners will develop a robust technical foundation. The course's emphasis on designing plugins tailored to business needs, integrating personas, and understanding the business context view of AI agents directly informs the advice an AI Consultant would provide. This enables the consultant to speak credibly about implementation details and potential architectures, rather than just high-level concepts, which is invaluable for guiding clients effectively.
Solutions Architect Artificial Intelligence
A Solutions Architect Artificial Intelligence designs and oversees the implementation of complex AI systems and solutions within an organization. This role requires a deep understanding of AI technologies, integration patterns, and cloud platforms to create scalable and robust architectures. This course may be useful for a Solutions Architect Artificial Intelligence by providing detailed, hands-on experience with a key integration framework, the Semantic Kernel SDK. Learners will explore the foundational concepts of LLMs and generative AI in a business context, set up development environments on Azure, and build functioning AI applications. The course's practical approach to creating intelligent agents, designing custom plugins, and implementing full-stack chat assistants provides valuable insights into the practical challenges and solutions in AI integration, which is essential for architects. Understanding how to integrate Azure OpenAI resources and apply techniques like RAG can directly inform architectural decisions for optimal performance and functionality.
Technical Product Manager Artificial Intelligence
A Technical Product Manager Artificial Intelligence defines the strategy, roadmap, and features for AI-powered products, bridging the gap between technical teams and business objectives. This role demands both strong product acumen and a solid understanding of AI technologies. This course may be helpful for a Technical Product Manager Artificial Intelligence by offering a profound, practical immersion into building intelligent applications with the Semantic Kernel SDK. Understanding how Large Language Models and generative AI are integrated, from environment setup to deployment of full-stack chat assistants, is invaluable. The course covers designing plugins to meet business needs, integrating personas, and managing prompts effectively, all of which directly relate to product feature definition and user experience. This technical depth enables a Technical Product Manager Artificial Intelligence to make informed decisions, communicate effectively with engineering teams, and anticipate development challenges when bringing AI-driven products to market.
Artificial Intelligence Research Scientist Applied
An Artificial Intelligence Research Scientist Applied typically focuses on translating cutting-edge AI research into practical applications and prototypes. This role often involves experimenting with new models, integration techniques, and deployment strategies for real-world impact. This course may be useful for an Artificial Intelligence Research Scientist Applied by providing a concrete framework, the Semantic Kernel SDK, for rapidly prototyping and implementing intelligent applications leveraging Large Language Models and generative AI. While not a theoretical research course, it offers deep practical insights into integrating AI models, creating custom plugins, and building full-stack AI-powered chat assistants. Understanding the practicalities of environment setup with Azure, prompt management, and RAG techniques is invaluable for applying research findings to functional systems. This course can help an Artificial Intelligence Research Scientist Applied to bridge the gap between theoretical knowledge and practical, deployable AI solutions. This role typically requires an advanced degree.
Data Scientist Machine Learning Applications
A Data Scientist Machine Learning Applications focuses on developing and deploying machine learning models to solve specific business problems, often bridging the gap between data insights and functional software. This role requires both analytical skills and practical implementation capabilities. This course may be helpful for a Data Scientist Machine Learning Applications by providing a robust framework for integrating Large Language Models and generative AI into real-world applications using the Semantic Kernel SDK. While not centered on statistical modeling or pure data analysis, the course’s emphasis on building intelligent agents, creating AI-powered chat applications, and extending functionality with custom plugins offers crucial implementation skills. Learners will understand how to set up development environments, configure Azure OpenAI resources, and apply techniques like RAG to enhance contextual accuracy, greatly aiding in the deployment and operationalization of advanced AI capabilities. This course can help a Data Scientist Machine Learning Applications to transition from model development to building interactive, AI-driven solutions. This role typically requires an advanced degree.

Reading list

We've selected 50 books that we think will supplement your learning. Use these to develop background knowledge, enrich your coursework, and gain a deeper understanding of the topics covered in Semantic Kernel SDK for Intelligent Applications .
Provides an in-depth look at Visual Studio Code, including how to use it to build web applications, mobile apps, and data science projects.
Provides a comprehensive guide to prompt engineering, covering techniques for crafting effective inputs to generative AI models. It's particularly useful for understanding how to obtain reliable and predictable results, which is crucial for both beginners and those looking to deepen their practical skills. This book is valuable as a current reference for anyone working with generative AI.
Is specifically designed to help readers prepare for the AZ-900 Microsoft Azure Fundamentals exam. It provides a broad overview of cloud concepts, core Azure services, security, privacy, compliance, and pricing. It serves as an excellent starting point for anyone new to Azure or cloud computing, providing foundational knowledge that is essential before diving into more specialized areas. This book is often used as a textbook or primary study guide for those seeking their first Azure certification.
Analyzing the engineering trade-offs of retrieval-augmented systems at enterprise scale, Chip Huyen covers lexical BM25 versus dense vector retrieval, reciprocal rank fusion, multimodal RAG, context window ordering, and retrieval latency optimization.
Demonstrating how to engineer a production RAG ingestion and inference pipeline alongside fine-tuned LLMs, Paul Iusztin and Maxime Labonne cover streaming feature pipelines, Qdrant vector databases, self-querying metadata filters, and hallucination telemetry.
Study guide for the AZ-104 exam, focusing on implementing and managing Azure infrastructure solutions. It covers topics like managing Azure identities and governance, implementing and managing storage, configuring and managing virtual networking, and managing Azure compute resources. It's a key resource for aspiring Azure Administrators.
Visualizing every stage of dense passage retrieval and grounded generation, Jay Alammar and Maarten Grootendorst teach contrastive embedding models, approximate nearest neighbor (ANN) graphs, reranking transformers, and RAG evaluation metrics.
Study guide for the AZ-305 exam, focusing on designing Microsoft Azure infrastructure solutions. It covers key architectural decisions related to compute, storage, networking, and security. It's essential for aspiring Azure Solutions Architects and provides in-depth knowledge required for designing complex Azure environments.
Gus Newton connects dense embedding pipelines with vector indexing strategies, guiding practitioners through chunking heuristics, hybrid lexical-semantic retrieval, and latency-aware RAG deployment.
Is widely considered a foundational text in Natural Language Processing (NLP), which is essential for chatbot development. It provides a comprehensive theoretical and practical introduction to the field, covering linguistic concepts and computational techniques. While substantial, it's an invaluable reference for those seeking a deep understanding of the underlying principles of how chatbots process and generate human language. It is often used as a textbook in university courses.
Provides a practical guide to using generative AI, covering the different techniques and tools available. It is written by two leading experts in the field, Josh Patterson and Adam Gibson.
Focuses on designing secure, scalable, and highly available applications on Azure. It delves into core architectural concepts, including serverless architecture, containers, Kubernetes, and big data solutions. It's essential for those looking to deepen their understanding of how to build robust and efficient solutions on the platform. This book is valuable for both aspiring and experienced Azure architects and can serve as a key reference for design patterns and best practices.
Dives deep into the complexities of systems with multiple interacting agents. It covers algorithmic, game-theoretic, and logical foundations, which are crucial for understanding how agents behave and coordinate in complex environments. It valuable reference for those looking to deepen their understanding beyond single-agent systems.
Offers a comprehensive overview of LLMs, covering their theoretical foundations, practical applications, and future directions.
Offers a practical, task-focused introduction to Azure, broken down into 21 easy-to-digest lessons. It covers core Azure concepts and services through hands-on labs, making it ideal for beginners who want to quickly gain practical experience. While not an exhaustive reference, it's highly valuable for solidifying fundamental understanding and getting productive with Azure in a short timeframe. It's well-regarded for its accessible approach to learning Azure basics.
Considered a classic in software engineering, this book introduces fundamental design patterns that are essential for building flexible and extensible systems. Understanding these patterns is crucial for designing and implementing plugin architectures effectively. must-read for anyone serious about software design and serves as a valuable reference.
Focusing on building LLM-powered autonomous agents, this book provides a practical framework for developing agents that can handle real-world tasks. It covers using tools like the OpenAI Assistants API and LangChain, making it very relevant for contemporary agent development.
Raj C Vaidyamath unpacks approximate nearest-neighbor algorithms like HNSW and IVF, showing how vector databases store, filter, and retrieve high-dimensional embeddings for production RAG workloads.
This cookbook offers practical recipes for developing WordPress plugins, covering a wide range of specific tasks and functionalities. It's a useful resource for hands-on learners and provides solutions to common plugin development challenges. It complements broader theoretical books with practical examples.
Manning, Raghavan, and Schutze's canonical Stanford reference establishes the mathematical foundations of inverted indexes, TF-IDF weighting, Okapi BM25 probabilistic retrieval, and precision-recall evaluation that anchor hybrid RAG architectures.
Identity and Access Management (IAM) is critical in cloud security. provides in-depth coverage of managing identities and access in Azure, including Azure Active Directory (now Microsoft Entra ID) and related services. It's a must-read for anyone responsible for securing Azure environments and managing user access.
Focuses on using the Hugging Face Transformers library, a popular tool for leveraging state-of-the-art transformer models in NLP. Given the prevalence of transformer models in modern chatbot development, especially with generative AI, this book is highly relevant for those looking to work with these advanced architectures. It's suitable for readers with some background in deep learning and NLP.
Reinforcement learning key paradigm for developing intelligent agents that can learn to make sequential decisions by interacting with their environment. is the classic text on the subject, providing a comprehensive introduction to the core concepts and algorithms used in training agents. It must-read for anyone focusing on learning agents.
Provides a comprehensive guide to monitoring and managing Azure environments. It covers selecting, deploying, and running Azure's monitoring and management services to simplify administration, reduce downtime, and optimize costs. It's a crucial resource for Azure administrators and operations professionals responsible for maintaining healthy and efficient Azure deployments.
Jimmy Lin, Rodrigo Nogueira, and Andrew Yates trace how BERT and T5 cross-encoders and bi-encoders transformed multi-stage document ranking, providing the theoretical and empirical backbone for dense passage retrieval and modern RAG rerankers.
Focusing on building and maintaining big data platforms on Azure, this book covers data management patterns, techniques, and best practices used within Microsoft. It's highly relevant for those interested in data engineering, ETL/ELT, and data governance on the Azure platform. provides practical guidance for setting up infrastructure, orchestration, workloads, and governance, making it a valuable resource for data professionals.
A hands-on guide specifically for developers, this book delves into the technology behind LLMs and provides practical guidance for building intelligent agents and applications. It's highly relevant for those looking to implement AI agents using LLMs.
Offers a practical, hands-on approach to prompt engineering specifically with ChatGPT. It's an excellent resource for high school and undergraduate students getting started, providing clear examples and exercises. It serves as a useful introductory guide and additional reading to complement foundational AI courses.
Provides a hands-on approach to prompt engineering with a focus on using the OpenAI API. It's particularly relevant for undergraduate students, graduate students, and working professionals who want to programmatically interact with LLMs. It serves as a practical guide for implementing prompt engineering techniques in applications.
Explains Azure DevOps and its components for implementing DevOps practices on Azure. It covers topics like CI/CD pipelines, source control, and artifact management within the Azure ecosystem. It's highly relevant for developers and operations professionals looking to streamline their application development and deployment processes using Azure DevOps.
Craig Knoblock and Pedro Szekely detail entity resolution, ontology alignment, and graph-structured knowledge representation, providing essential foundations for GraphRAG architectures that go beyond flat vector similarity.
Offers a practical approach to designing and implementing single and multi-agent systems, particularly in the context of generative AI. It helps bridge the gap between theoretical concepts and real-world deployment of AI agents. It is highly relevant for understanding contemporary applications.
Focuses on the creative aspects of prompt engineering and generating diverse language outputs. It's a good fit for students and professionals looking to go beyond basic prompting and explore more advanced techniques for creative content generation. It adds breadth by covering applications in areas like creative writing and podcasting.
Focuses on building applications and agents using Large Language Models. It's a practical guide for developers looking to leverage LLMs in creating intelligent agents. It provides hands-on knowledge relevant to contemporary AI agent development.
Focuses on Azure services relevant to developers, particularly Platform as a Service (PaaS) offerings like App Service, Functions, and databases. It guides developers in building and deploying applications on Azure. It's a valuable resource for developers looking to leverage Azure's cloud capabilities and understand best practices for cloud-native development.
Provides a highly accessible introduction to design patterns, which are fundamental to creating extensible software, including plugin architectures. It uses a visually rich format to help solidify understanding of core object-oriented design principles. While not exclusively about plugins, the patterns covered are directly applicable to designing systems that can be extended through plugins. This book is valuable as foundational reading.
Explores various architectural perspectives within Azure, covering infrastructure, application, data, and security architecture. It uses 'maps' to illustrate how different Azure services can be combined to build solutions. This book is particularly useful for understanding cloud-native concepts and how to design comprehensive solutions on Azure. It's a good resource for architects and developers looking to gain a broader and deeper view of Azure's capabilities.
Provides a deep dive into Azure Policy, a service for creating, assigning, and managing policies to enforce organizational standards and assess compliance. It's essential for administrators and security professionals responsible for governance and compliance in Azure environments. This book serves as a detailed guide to implementing and utilizing Azure Policy effectively.
Provides a solid introduction to the field of multiagent systems, covering key concepts, architectures, and applications. It's more accessible than some of the deeper theoretical texts and serves as an excellent starting point for understanding the principles behind multiple interacting intelligent agents.
A comprehensive guide aimed at making prompt engineering accessible to a wide audience. It covers various techniques and applications for leveraging AI language models effectively. is useful for high school students through working professionals seeking a thorough introduction and practical guidance.
Diagnosing why relevant passages fail to surface requires deep mastery of tokenization, query expansion, field boosting, and relevance tuning. Doug Turnbull and John Berryman teach systematic relevance engineering essential for high-recall RAG.
Examines the transformative role of autonomous intelligent systems in business and the workplace. It explores the concepts of autonomy and collaborative intelligence in AI agents and their potential impact on various industries. It's a good resource for understanding the broader implications and applications of agentic AI.
Focuses on Azure Infrastructure as a Service (IaaS), guiding readers on migrating on-premises infrastructure to Azure and building scalable and secure cloud solutions. It covers design and best practices for building highly available and secure solution stacks using Azure IaaS components. This book is particularly useful for IT professionals involved in cloud migration and managing virtual machines and networks in Azure.
A recipe-based guide to building and managing ETL/ELT pipelines using Azure Data Factory (ADF). is practical and problem-solution oriented, covering various aspects of ADF, Azure Synapse, and data integration. It's an excellent resource for data engineers and ETL developers working with Azure's data services, providing hands-on examples for common tasks.
This guide aims to make prompt engineering accessible with a step-by-step approach. It is well-suited for beginners and those new to the field, including high school students and those in introductory undergraduate programs. It provides practical tips and is useful for gaining a broad understanding of how to formulate effective AI prompts.
For those interested in data science and machine learning on Azure, this book provides practical guidance on using Azure Machine Learning services. It covers building, training, and deploying machine learning models on the Azure platform. It's a valuable resource for data scientists and ML engineers leveraging Azure for their projects.
Alberto Paro delivers practical recipes for inverted-index tuning, BM25 scoring, and dense vector kNN queries in Elasticsearch 8, equipping engineers to build hybrid lexical-semantic search backends for RAG.
Focusing on Azure Bicep, a declarative language for deploying Azure resources, this book is relevant for anyone using or planning to use Infrastructure as Code with Bicep. It covers Bicep fundamentals, modules, and best practices for automating Azure deployments. It's a practical guide for developers and operations professionals working with Azure resource deployment.

Share

Help others find this course page by sharing it with your friends and followers:

Similar courses

Here are nine courses similar to Semantic Kernel SDK for Intelligent Applications .
Generative AI Applications and Popular Tools
Most relevant
Generative AI with Large Language Models
Most relevant
Harnessing LLMs & Text-Embeddings API with Google Vertex...
Most relevant
Generative AI Teach-Out
Most relevant
Automated Reasoning with GPT Assistant API: ReAct Agents
Most relevant
Generative AI for Developers: Unit 3
Most relevant
Current Issues in Ethics and AI
Most relevant
Generative AI Apps with ChatGPT, LangChain & Hugging Face
Most relevant
From Java Dev to AI Engineer: Spring AI Fast Track
Most relevant

Coursera Buyer Protection & Guarantee

Verified partner policies & purchase protections

Accredited University Partner
Free Trial & Audit

7-Day Free Trial & Free Audit

7-day free trial on monthly Coursera Plus subscriptions; free audit option available on most individual courses to explore video lectures and readings at no charge.

Return & Refund Policy

14-Day Refund Guarantee

14-day refund window on annual Coursera Plus subscriptions and single-course purchases prior to certificate issuance. Monthly subscriptions do not offer refunds once billed.

Buyer Protections

Verified Academic & Industry Partner

Accredited university and industry certifications (e.g. Stanford, Google, IBM, Yale), secure SSL payment processing, and verifiable digital certificate links.

Key Purchase Protections
14-day refund window on annual Coursera Plus and single courses
7-day free trial on monthly Coursera Plus subscriptions
Free course audit option for lectures and readings
Verified certificates from top universities & companies
OpenCourser Verified Partner Policy details last reviewed: 2026-10-22
Our mission

OpenCourser helps millions of learners each year. People visit us to learn workspace skills, ace their exams, and nurture their curiosity.

Our extensive catalog contains over 50,000 courses and twice as many books. Browse by search, by topic, or even by career interests. We'll match you to the right resources quickly.

Find this site helpful? Tell a friend about us.

Affiliate disclosure

We're supported by our community of learners. When you purchase or subscribe to courses and programs or purchase books, we may earn a commission from our partners.

Your purchases help us maintain our catalog and keep our servers humming without ads.

Thank you for supporting OpenCourser.

© 2016 - 2025 OpenCourser