Lorsque vous vous inscrivez à ce cours, vous êtes également inscrit(e) à cette Spécialisation.
Apprenez de nouveaux concepts auprès d'experts du secteur
Acquérez une compréhension de base d'un sujet ou d'un outil
Développez des compétences professionnelles avec des projets pratiques
Obtenez un certificat professionnel partageable
Il y a 4 modules dans ce cours
This course introduces the principles and practice of AI Agent Orchestration and Scaling, blending conceptual understanding with hands-on system design. You’ll learn how to coordinate, monitor, and optimize multiple AI agents that work together to deliver intelligent, autonomous workflows — with a special focus on building scalable customer support solutions powered by AI.
Through structured lessons, guided projects, and practical demonstrations, you’ll explore how to orchestrate agent interactions, assign tasks dynamically, and ensure system reliability as agent complexity increases. You’ll work with orchestration patterns and communication protocols that allow AI agents to reason collectively, respond to user input, and handle real-time decision-making.
By the end of this course, you will be able to:
• Understand orchestration frameworks and scaling strategies for AI agent systems.
• Implement coordination and monitoring techniques for autonomous agent workflows.
• Optimize task management, load balancing, and performance in multi-agent environments.
• Design scalable customer support agents that handle queries, adapt behavior, and improve with feedback.
This course is ideal for AI developers, data scientists, and automation engineers who want to build enterprise-ready AI systems that perform efficiently at scale.
A basic understanding of Python programming and prior experience with AI or machine learning will be helpful but not mandatory.
Join us to explore how orchestration and scaling turn simple AI agents into intelligent, autonomous systems capable of managing complex, real-world operations.
This module explores multimodal AI and stateful orchestration using LangGraph to build intelligent, context-aware agents. You’ll learn to connect visual, textual, and API inputs for real-time problem diagnosis and decision-making. By the end, you’ll have built a visually informed, multi-tool triage agent capable of handling complex, multimodal workflows autonomously.
Inclus
12 vidéos5 lectures4 devoirs
Afficher les informations sur le contenu du module
12 vidéos•Total 62 minutes
Specialization Introduction•5 minutes
Course Introduction•3 minutes
The Shift from Digital Collaboration to True Autonomy•5 minutes
Tool Mastery: LangGraph Defining the Graph State and Nodes•5 minutes
Hands-on: Creating the First LangGraph Flow and Executing It•5 minutes
Hands-on: Implementing the Tier-1 Triage Node and Conditional Routing•6 minutes
Tool Mastery: Vision LLMs Principles of Visual AI and Multimodal Reasoning•5 minutes
Hands-On: Using Vision LLMs to Extract Error Codes from Customer Screenshots•5 minutes
Hands-on: Integrating External API Tools•6 minutes
Hands-on: Building the Multi-Tool Orchestration Node: Sequential Diagnostic Logic•5 minutes
Hands-On: Setting up the Simulated Chat Interface Input/Output•7 minutes
Hands-on: The Visually-Informed Triage Agent•4 minutes
5 lectures•Total 50 minutes
Course Outline: AI Agent Orchestration and Scaling•10 minutes
Foundations of LangGraph and State•10 minutes
Multimodal Input and Real-Time Diagnosis•10 minutes
Building the Agent•10 minutes
Multimodal Inputs and Stateful Orchestration•10 minutes
4 devoirs•Total 33 minutes
Knowledge Check: Multimodal Inputs and Stateful Orchestration•15 minutes
Practice Quiz: Foundations of LangGraph and State•6 minutes
Practice Quiz: Multimodal Input and Real-Time Diagnosis•6 minutes
Practice Quiz: RAG for Financial Data•6 minutes
Long-Term Memory and Dynamic Re-Planning
Module 2•2 heures à terminer
Détails du module
This module focuses on enabling long-term memory and dynamic re-planning in autonomous agents. You’ll learn to design knowledge graphs and memory modules that let agents recall past experiences and adapt their actions. By the end, you’ll build a self-correcting, feedback-driven agent capable of real-time learning and continuous improvement through long-term memory integration.
Inclus
10 vidéos4 lectures4 devoirs
Afficher les informations sur le contenu du module
10 vidéos•Total 53 minutes
LTM Theory(Episodic vs. Semantic Memory in Autonomous Systems)•5 minutes
Hands-on: Implementing the LTM Check Node•6 minutes
Hands-on: The Planner Agent's Role•5 minutes
Hands-on: The Re-Planning Node Logic•4 minutes
Hands-on: Building the User Feedback Loop•5 minutes
Hands-on: Implementing Sub-Graphs for Nested Tasks•7 minutes
Hands-on: The Agent Demonstrates LTM-Informed Dynamic Re-Planning•5 minutes
4 lectures•Total 40 minutes
LTM Architecture and Knowledge Graphs•10 minutes
Retrieval and Integration Logic•10 minutes
Self-Correction and Dynamic Flow•10 minutes
Long-Term Memory and Dynamic Re-Planning•10 minutes
4 devoirs•Total 33 minutes
Knowledge Check: Long-Term Memory and Dynamic Re-Planning•15 minutes
Practice Quiz: LTM Architecture and Knowledge Graphs•6 minutes
Practice Quiz: Retrieval and Integration Logic •6 minutes
Practice Quiz: Self-Correction and Dynamic Flow •6 minutes
Orchestration, Governance, and Scaling
Module 3•2 heures à terminer
Détails du module
This module brings together orchestration, governance, and large-scale deployment of autonomous agents. You’ll implement guardrails, audit trails, and human-in-the-loop controls for safe operations, then deploy and scale workflows and containerization. By the end, you’ll have an end-to-end, production-ready autonomous system capable of governed, scalable decision-making.
Inclus
11 vidéos4 lectures4 devoirs
Afficher les informations sur le contenu du module
11 vidéos•Total 57 minutes
The Irreversible Action Guardrail: Preventing High-Risk Workflow Execution•5 minutes
Hands-on: Human-in-the-Loop Integrating a Manual Hand-off Node•6 minutes
Data Governance: Automating the Audit Trail and Decision Logging•5 minutes
Hands-on: Flask - Setting up the Agent’s API Service•5 minutes
Hands-on: Flask - Deploying the Full LangGraph Workflow for Production Access•5 minutes
Hands-on: Scaling Concepts: Edge Agents vs. Cloud Orchestration•6 minutes
Kubernetes/Containerization for Fleet Management•5 minutes
Hands-on: Connecting all Modules into the Support Agent•6 minutes
Hands-on: Testing and Validating the Autonomous Workflow•6 minutes
Hands-on: Integrating LangSmith for LLM Monitoring and Observability•4 minutes
The Future of Autonomous Process Optimization•5 minutes
4 lectures•Total 40 minutes
Orchestration, Governance, and Scaling•10 minutes
Production Deployment and Scaling•10 minutes
Integration and Next Steps•10 minutes
Orchestration, Governance, and Scaling•10 minutes
4 devoirs•Total 33 minutes
Knowledge Check: Orchestration, Governance, and Scaling•15 minutes
Practice Quiz: Governance and Guardrails•6 minutes
Practice Quiz: Production Deployment and Scaling •6 minutes
Practice Quiz: Integration and Next Steps•6 minutes
Course Wrap-Up and Assessment
Module 4•2 heures à terminer
Détails du module
This module provides learners with an opportunity to synthesize their knowledge and demonstrate mastery of AI systems. Learners will review key concepts from memory-augmented agents, real-time data integration, multimodal orchestration, and governance frameworks. They will complete graded, scenario-based assessments to apply their understanding in building and managing collaborative, secure, and scalable agent ecosystems.
Inclus
1 vidéo1 lecture2 devoirs
Afficher les informations sur le contenu du module
1 vidéo•Total 2 minutes
Course Summary•2 minutes
1 lecture•Total 30 minutes
Practice Project: Autonomous Multimodal Support Agent•30 minutes
2 devoirs•Total 60 minutes
End Course Knowledge Check: AI Agent Orchestration and Scaling•30 minutes
AI Support Agent: Scenario Assignment•30 minutes
Obtenez un certificat professionnel
Ajoutez ce titre à votre profil LinkedIn, à votre curriculum vitae ou à votre CV. Partagez-le sur les médias sociaux et dans votre évaluation des performances.
Edureka is an online education platform focused on delivering high-quality learning to working professionals. We have the
highest course completion rate in the industry and we strive to create an online ecosystem for our global learners to equip
themselves with industry-relevant skills in today’s cutting edge technologies.
Pour quelles raisons les étudiants sur Coursera nous choisissent-ils pour leur carrière ?
Felipe M.
Étudiant(e) depuis 2018
’Pouvoir suivre des cours à mon rythme à été une expérience extraordinaire. Je peux apprendre chaque fois que mon emploi du temps me le permet et en fonction de mon humeur.’
Jennifer J.
Étudiant(e) depuis 2020
’J'ai directement appliqué les concepts et les compétences que j'ai appris de mes cours à un nouveau projet passionnant au travail.’
Larry W.
Étudiant(e) depuis 2021
’Lorsque j'ai besoin de cours sur des sujets que mon université ne propose pas, Coursera est l'un des meilleurs endroits où se rendre.’
Chaitanya A.
’Apprendre, ce n'est pas seulement s'améliorer dans son travail : c'est bien plus que cela. Coursera me permet d'apprendre sans limites.’
The course aims to teach how to design, build, and scale autonomous agents that can reason, plan, and act using LangGraph integrating multimodal inputs, long-term memory, and dynamic orchestration for enterprise environments.
What is LangGraph, and how is it different from LangChain?
LangGraph extends LangChain by focusing on stateful orchestration — allowing developers to create graph-based agent workflows with persistent state, conditional routing, and memory-aware decision nodes.
Why are multimodal inputs important for autonomous agents?
Multimodal inputs (text, image, voice, etc.) enable agents to understand real-world contexts more accurately. For example, diagnosing issues from screenshots or combining text and visual data for richer reasoning.
How does Long-Term Memory (LTM) improve agent intelligence?
LTM allows agents to store and recall prior experiences, user interactions, or problem contexts, enabling personalized responses, adaptive learning, and better decision-making over time.
What is the role of Knowledge Graphs in this architecture?
Knowledge Graphs model relationships between users, tools, and error patterns — serving as a semantic backbone for reasoning and context retrieval within the agent’s memory system.
How do governance and guardrails protect the system in production?
Governance mechanisms, like irreversible action guardrails and audit trails, ensure agents act safely, comply with policies, and route high-risk actions through human-in-the-loop checks.
Can these LangGraph agents be deployed at scale?
Yes. The course covers deployment via Flask APIs, containerization (Docker/Kubernetes), and scaling strategies for distributed or edge-based agent orchestration.
What kind of real-world applications can learners build after this course?
Learners can design enterprise-grade support or diagnostic agents that analyze multimodal data, plan tasks dynamically, perform self-correction, and integrate with real-time APIs for autonomous decision-making.
When will I have access to the lectures and assignments?
To access the course materials, assignments and to earn a Certificate, you will need to purchase the Certificate experience when you enroll in a course. You can try a Free Trial instead, or apply for Financial Aid. The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.
What will I get if I subscribe to this Specialization?
When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.
Is financial aid available?
Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.