К содержимому
learnspaceYOUR NEXT CHAPTER
ПРОСТРАНСТВО ОБУЧЕНИЯ
ГлавнаяКаталог курсовМоё обучениеCoursera

Знания без границ

Учитесь у лучших университетов и компаний мира.

Открыть Coursera
Интеграция
Пространство университета
Моё пространствоСтраница курса
↵
ЯЛичный кабинетСтудент
© 2026 LearnSpaceКаждый день — возможность узнать больше.Помощь
Building Intelligent Troubleshooting Agents · LearnSpace
Назад в каталог
courseraПрограммирование

Building Intelligent Troubleshooting Agents

Курс от Microsoft
Средний≈ 45.5 чАнглийский
О курсеНавыкиПрограммаПреподаватели

О курсе

This course focuses on the design and implementation of intelligent troubleshooting agents. You will learn to create AI-powered agents that can diagnose and resolve issues autonomously. The course covers natural language processing, decision-making algorithms, and best practices in AI agent development. By the end of this course, you will be able to: 1. Define, describe, and design the architecture of an intelligent troubleshooting agent. 2. Implement natural language processing techniques for user interaction. 3. Develop decision-making algorithms for problem diagnosis and resolution. 4. Optimize and evaluate the performance of AI-based troubleshooting agents. To be successful in this course, you should have intermediate programming knowledge of Python, plus experience with AI & ML infrastructure and core algorithms and techniques, including approaches using pretrained large-language models (LLMs). Familiarity with statistics is also recommended.

Навыки, которые вы освоите

Natural Language ProcessingFine-tuningLarge Language ModelingModel EvaluationModel OptimizationArtificial IntelligencePerformance TestingDecision IntelligenceUser Interface (UI)Decision Support SystemsAgentic WorkflowsModel TrainingLLM ApplicationAgentic systemsGenerative AI AgentsTest CaseClassification AlgorithmsMachine Learning AlgorithmsApplied Machine Learning

Программа курса

5 модулей · 164 учебных материалов

01LLM fine-tuning for task-specific adaptation53 материалов

Welcome to the course

Introduction to the AI/ML engineering advanced professional certificate programВидеоIntroduction to LLM fine-tuning for task-specific adaptationВидеоThe importance of fine-tuning an LLMВидеоWelcome to the Coursera CommunityЧтение

Учитесь у экспертов

Microsoft

Преподаватель курса

Building Intelligent Troubleshooting Agents
В каталоге вашей программы

Инвестируйте в себя

Новые знания — в удобное для вас время.

Начать на Coursera

Обучение откроется на Coursera
в новой вкладке

Обучение на Coursera

≈ 45.5 ч

5 модулей

Язык: Английский

Субтитры: Арабский, Французский, Узбекский, Украинский, Китайский (Китай), Греческий, Итальянский, Бразильский португальский, Вьетнамский, Нидерландский, Корейский, Немецкий, Пушту, Русский, Тайский, Индонезийский, Шведский, Турецкий, Азербайджанский, Испанский, Хинди, Японский, Казахский, Венгерский, Польский

Часть программы вашего университета
Microsoft updatesЧтение
Practice activity: Setting up your environment in Microsoft AzureЧтение
Reflection: Setting up your environment in Microsoft AzureЗадание
Walkthrough: Setting up your environment in Microsoft Azure (Optional)Чтение
Practice activity: Creating your code repositoryЧтение
Reflection: Creating your code repositoryЗадание
Walkthrough: Creating your code repository Part 1 (Optional)Видео
Walkthrough: Creating your code repository Part 2 (Optional)Видео
Course syllabusЧтение

Introduction to LLM fine-tuning

Overview of LLM fine-tuningЧтениеLLM Fine-Tuning: Principles and StepsЧтениеPractice activity: LLM fine-tuningЧтениеReflection: LLM fine-tuningЗадание Walkthrough: LLM fine-tuning (Optional)ЧтениеDetailed explanation of principles and steps of LLM fine-tuningЧтениеReview: Principles and steps of LLM fine-tuningЧтение

Selecting and preparing data for fine-tuning

Selecting and preparing data for fine-tuningЧтениеUse case demonstration: Selecting and preparing data for fine-tuningВидеоPractice activity: Model and dataset selectionЧтениеReflection: Model and dataset selectionЗаданиеWalkthrough: Model and dataset selection (Optional)ЧтениеPractice activity: Preparing a dataset for fine-tuningЧтениеReflection: Preparing a dataset for fine-tuningЗаданиеWalkthrough: Preparing a dataset for fine-tuning (Optional)Видео

Fine-tuning techniques

Fine-tuning techniquesЧтениеPractice activity: Applying PEFTЧтениеReflection: Applying PEFTЗаданиеWalkthrough: Applying PEFT (Optional)ЧтениеPractice activity: Applying LoRAЧтениеReflection: Applying LoRAЗаданиеWalkthrough: Applying LoRA (Optional)ЧтениеPractice activity: Applying QLoRAЧтениеReflection: Applying QLoRAЗаданиеWalkthrough: Applying QLoRA (Optional)ЧтениеPractice activity: Comparing fine-tuning techniquesЧтениеReflection: Comparing fine-tuning techniquesЗаданиеWalkthrough: Comparing fine-tuning techniques (Optional)ВидеоKnowledge check: Fine-tuning techniquesЗадание

Evaluating fine-tuned models

Evaluating fine-tuned modelsЧтениеDetailed explanation of evaluation metricsЧтениеPractice Activity: Applying evaluation metrics in fine-tuning modelsЧтениеReflection: Applying evaluation metrics in fine-tuning modelsЗаданиеWalkthrough: Applying evaluation metrics in fine-tuning models (Optional)ЧтениеThe relevance of evaluation metricsВидео

Module summary: LLM fine-tuning for task-specific adaptation

Summary: Fine-tuning LLMsВидеоPractice activity: Fine-tuning an LLMЧтениеReflection: Fine-tuning an LLMЗаданиеWalkthrough: Fine-tuning an LLM (Optional)ВидеоGraded quiz: Fine-tuning LLMsЗадание
02Fundamentals of AI agents25 материалов

Introduction to AI agents

Introduction to AI agentsВидеоDetailed explanation of principles and architecture of AI agentsЧтениеKnowledge check: AI agentsЗадание

Multiagent systems

Understanding multi-agent systemsЧтениеPrinciples of multi-agent systemsЧтениеDifferences in multi-agent systemsВидеоUse case demonstration: Multi-agent systemsВидеоPractice activity: Multi-agent systems vs. single agent systemsЧтениеReflection: Multi-agent systems vs. single agent systemsЗаданиеWalkthrough: Multi-agent systems vs. single agent systems (Optional)ЧтениеKnowledge check: Multi-agent systemsЗадание

Designing intelligent troubleshooting agents

Designing intelligent troubleshooting agentsЧтениеRequirements definition for intelligent troubleshooting agentsЧтениеKnowledge check: Designing intelligent troubleshooting agentsЗадание

Requirements for effective AI troubleshooting

Requirements for effective AI troubleshootingЧтениеPractice activity: Key requirements for AI troubleshootingЧтениеReflection: Key requirements for AI troubleshootingЗаданиеWalkthrough: Key requirements for AI troubleshooting (Optional)ЧтениеReal-world examples: Effective AI troubleshootingВидеоDiscussion: Best practices for AI troubleshootingЧтение

Module summary: Fundamentals of AI agents

Summary: AI agentsЧтениеPractice activity: Designing an intelligent troubleshooting agentЧтениеReflection: Designing an intelligent troubleshooting agentЗаданиеWalkthrough: Designing an intelligent troubleshooting agent (Optional)ВидеоGraded quiz: AI agentsЗадание
03Natural language processing for troubleshooting24 материалов

Introduction to NLP for troubleshooting

Overview of natural language processing (NLP) techniquesВидеоDetailed explanation: principles and applications of NLPЧтениеKnowledge check: NLP techniquesЗадание

Developing a chatbot interface

Developing a chatbot interfaceЧтениеPractice activity: Developing the chatbot interfaceЧтениеReflection: Developing the chatbot interfaceЗаданиеWalkthrough: Developing the chatbot interface (Optional)Видео

Sentiment analysis

Overview: sentiment analysisЧтениеUse case demonstration: Sentiment analysisВидеоExplanation of sentiment analysisЧтениеPractice activity: Implementing sentiment analysisЧтениеReflection: Implementing sentiment analysisЗаданиеWalkthrough: Implementing sentiment analysis (Optional)Видео

Integrating NLP components

Integrating NLP componentsЧтениеBest practices for integrating NLP componentsВидеоPractice activity: Integrating NLP componentsЧтениеReflection: Integrating NLP componentsЗаданиеWalkthrough: Integrating NLP components (Optional)Чтение

Module summary: Natural language processing for troubleshooting

Module summary: NLP for troubleshootingВидеоPractice activity: Implementing NLP for troubleshootingЧтениеReflection: Implementing NLP for troubleshootingЗаданиеWalkthrough: Implementing NLP for troubleshooting (Optional)ВидеоGraded quiz: Implementing NLP for troubleshootingЗадание
04Implementing the troubleshooting agent34 материалов

Core functionality of a troubleshooting agent

Core functionality of a troubleshooting agentЧтениеExplanation of key componentsЧтениеPractice activity: Coding in PythonЧтениеReflection: Coding in PythonЗаданиеWalkthrough: Coding a troubleshooting agent in Python (Optional)Видео

Problem classification models

Problem classification modelsЧтениеExplanation of classification modelsЧтениеPractice activity: Implementing classification modelsЧтениеReflection: Implementing classification modelsЗаданиеWalkthrough: Implementing classification models (Optional)ВидеоPractice activity: Implementing and evaluating classification modelsЧтениеReflection: Implementing and evaluating classification modelsЗаданиеWalkthrough: Implementing and evaluating classification models (Optional)Чтение

Decision-making algorithms

Decision-making algorithmsЧтениеHow to implement a decision-making algorithm in PythonВидеоPractice activity: Creating a decision-making algorithm in PythonЧтениеReflection: Creating a decision-making algorithm in PythonЗаданиеWalkthrough: Creating a decision-making algorithm in Python (Optional)ЧтениеPractice activity: Solution recommendationЧтение

Error handling and logging

Error handling and loggingЧтениеExplanation of error handlingЧтениеPractice activity: Implementing mechanismsЧтениеReflection: Implementing mechanismsЗаданиеWalkthrough: Implementing mechanisms (Optional)ЧтениеPractice activity: LoggingЧтение

Module summary: Implementing the troubleshooting agent

Summary: Troubleshooting agentsЧтениеPractice activity: Implementing the troubleshooting agentЧтениеReflection: Implementing the troubleshooting agentЗаданиеWalkthrough: Implementing the troubleshooting agent (Optional)ВидеоGraded quiz: Troubleshooting agentsЗадание
05Testing and optimizing the agent28 материалов

Designing test cases

Designing test casesВидеоExplanation of test case designЧтениеPractice activity: Designing test cases for ML systemsЧтениеReflection: Designing test cases for ML systemsЗаданиеWalkthrough: Designing test cases for ML systems (Optional)ВидеоHear from an expert: Accounting for cultural, language, and contextual nuancesВидео

Optimizing response time and accuracy

Optimizing response time and accuracyЧтениеExplanation of optimization techniquesВидеоPractice activity: Implementing optimization techniquesЧтениеReflection: Implementing optimization techniquesЗаданиеWalkthrough: Implementing optimization techniques (Optional)Видео

Evaluating agent effectiveness

Evaluating agent effectivenessЧтениеPractice activity: Evaluating agent effectivenessЧтениеReflection: Evaluating agent effectivenessЗаданиеWalkthrough: Evaluating agent effectiveness (Optional)ВидеоHear from an expert: Designing with the end user in mindВидео

Module summary: Testing and optimizing the agent

Summary: Testing and optimizing the agentВидеоPractice activity: Testing and optimizing the agentЧтениеReflection: Testing and optimizing the agentЗаданиеWalkthrough: Testing and optimizing the ML agent (Optional)ВидеоGraded quiz: Testing and optimizing the agentЗаданиеHear from an expert: Resolving unexpected issues during implementationВидео

Course summary: Building Intelligent Troubleshooting Agents

Course summaryВидеоCourse assignment: Producing a troubleshooting agentЧтениеReflection: Producing a troubleshooting agentЗаданиеWalkthrough: Producing a troubleshooting agent (Optional)ВидеоCourse assignment: Drafting the technical reportВзаимная проверкаCongratulations on completing the course!Видео
Knowledge check: Sentiment analysisЗадание
Reflection: Solution recommendationЗадание
Walkthrough: Creating a solution recommendation system (Optional)Видео
Reflection: LoggingЗадание
Walkthrough: Implementing logging in ML systems (Optional)Видео