What job roles is this course designed for?

<text variant="body1">This capstone enables you to demonstrate your job-ready skills for advanced roles such as AI Agent Engineer, RAG Systems Developer, MCP Developer, Generative AI Application Engineer, Multi-Agent Systems Developer, and AI Workflow Engineer. <text variant="body1">It is ideal for software developers, Python programmers, and AI practitioners who want hands-on experience building and deploying multimodal RAG systems, integrating tools using Model Context Protocol (MCP), and orchestrating multi-agent workflows. <text variant="body1">The course is also well suited for professionals reskilling into generative AI engineering roles that require end-to-end system design, tool integration, and production-ready AI application development.

What prior knowledge is essential for this course?

You should be comfortable with Python programming and have a foundational understanding of large language models (LLMs), embeddings, and retrieval-based workflows. Familiarity with RAG concepts and basic agent architectures will help you progress more smoothly. Completing the earlier courses in one of the related IBM Professional Certificates and specializations is strongly recommended, as this capstone builds on newly learnt concepts and applies them in an end-to-end implementation.

What tools and technologies will I learn in this course?

You’ll work with large language models (LLMs) and multimodal LLMs to structure data, generate embeddings, and build retrieval pipelines. You’ll design multimodal vector indexes, implement similarity-based retrieval with metadata filtering, and apply late-fusion ranking techniques. You’ll also develop multi-agent systems using LangChain and LangGraph, build an interactive Gradio chatbot interface, and integrate agents, retrieval systems, and tools using Model Context Protocol (MCP) by configuring servers, clients, and an LLM-based host.

What practical skills will I gain from this course?

You’ll learn how to structure unstructured text and multimodal data using LLMs, build multimodal vector indexes, and implement similarity-based retrieval with metadata filtering and ranking techniques. You’ll also design and test a multi-agent recommendation system, build an interactive Gradio chatbot interface, and integrate agents, retrieval systems, and tools using Model Context Protocol (MCP) to create an end-to-end generative AI application.

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 Certificate?

When you enroll in the course, you get access to all of the courses in the Certificate, 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.

RAG and Agentic AI Capstone Project

kurs ist nicht verfügbar in Deutsch (Deutschland)

Wir übersetzen es in weitere Sprachen.

RAG and Agentic AI Capstone Project

Dieser Kurs ist Teil von IBM RAG and Agentic AI (berufsbezogenes Zertifikat)

Dozenten: Abdul Fatir

2.112 bereits angemeldet

Bei enthalten

Mehr erfahren

5 Module

Verschaffen Sie sich einen Einblick in ein Thema und lernen Sie die Grundlagen.

15 Bewertungen

Stufe Fortgeschritten

Empfohlene Erfahrung

1 Woche zu vervollständigen

unter 10 Stunden pro Woche

Flexibler Zeitplan

In Ihrem eigenen Lerntempo lernen

5 Module

Verschaffen Sie sich einen Einblick in ein Thema und lernen Sie die Grundlagen.

15 Bewertungen

Stufe Fortgeschritten

Empfohlene Erfahrung

1 Woche zu vervollständigen

unter 10 Stunden pro Woche

Flexibler Zeitplan

In Ihrem eigenen Lerntempo lernen

Was Sie lernen werden

Demonstrate you have the job-ready skills to design and implement a complete AI system from data to deployment.
Transform unstructured text and multimodal data into structured JSON formats using LLMs to drive data-driven decision-making.
Architect multimodal vector databases and multi-agent systems to coordinate specialized agents for high-accuracy recommendations.
Integrate complex AI ecosystems using MCP, configuring servers and clients to build, validate, and scale tool-augmented agents.

Kompetenzen, die Sie erwerben

Kategorie: Tool Calling
Kategorie: Large Language Modeling
Kategorie: Unstructured Data
Kategorie: System Testing
Kategorie: Generative AI Agents
Kategorie: Multimodal Prompts
Kategorie: Embeddings
Kategorie: Retrieval-Augmented Generation
Kategorie: Agentic systems
Kategorie: LLM Application

Werkzeuge, die Sie lernen werden

Kategorie: Agentic Workflows
Kategorie: JSON
Kategorie: Vector Databases
Kategorie: Generative AI
Kategorie: AI Orchestration
Kategorie: Model Context Protocol
Kategorie: AI Workflows

Wichtige Details

Zertifikat zur Vorlage

Zu Ihrem LinkedIn-Profil hinzufügen

Kürzlich aktualisiert!

März 2026

Bewertungen

16 Aufgaben

Unterrichtet in Englisch

Erfahren Sie, wie Mitarbeiter führender Unternehmen gefragte Kompetenzen erwerben.

Weitere Informationen zu Coursera für Unternehmen

Logos von Petrobras, TATA, Danone, Capgemini, P&G und L'Oreal

Erweitern Sie Ihr Fachwissen im Bereich Software Development

Dieser Kurs ist Teil der Spezialisierung IBM RAG and Agentic AI (berufsbezogenes Zertifikat)

Wenn Sie sich für diesen Kurs anmelden, werden Sie auch für dieses berufsbezogene Zertifikat angemeldet.

Lernen Sie neue Konzepte von Branchenexperten
Gewinnen Sie ein Grundverständnis bestimmter Themen oder Tools
Erwerben Sie berufsrelevante Kompetenzen durch praktische Projekte
Erwerben Sie ein Berufszertifikat von IBM zur Vorlage

In diesem Kurs gibt es 5 Module

Demonstrate you have the job-ready skills to design and implement a complete AI system from data to deployment, with this portfolio-worthy RAG and Agentic AI Capstone Project from IBM.

You’ll design and build a production-style multimodal RAG system that combines structured data, embeddings, retrieval logic, evaluation strategies, and intelligent workflows into one cohesive, scalable solution. You’ll create and manage structured JSON datasets, generate text and image embeddings, and construct a vector database to power accurate similarity search and metadata-filtered retrieval. As you progress, you’ll implement robust RAG pipelines, apply re-ranking and evaluation techniques, and strengthen response quality using multimodal inputs and systematic validation approaches. You’ll also design a multi-agent recommendation system, integrate tools using the Model Context Protocol (MCP), orchestrate workflow testing, and launch an interactive Gradio chatbot interface. By the end, you’ll have developed an end-to-end generative AI application that demonstrates practical AI engineering expertise, architectural thinking, and production-ready implementation skills.

Moduldetails

In this module, you will use LLMs to transform unstructured restaurant descriptions into structured JSON files by designing prompts and extracting predefined attributes. You will apply multimodal LLMs to generate captions from review images and integrate those captions into structured user review data. Finally, you will build a command-line Python interface to browse, add, edit, and delete restaurant records, integrate LLM-powered structuring functions for new entries, and implement file backup mechanisms before saving updates.

Das ist alles enthalten

2 Videos1 Lektüre4 Aufgaben3 App-Elemente5 Plug-ins

2 VideosInsgesamt 5 Minuten

Course Introduction3 Minuten
Project Overview2 Minuten

1 LektüreInsgesamt 2 Minuten

Course Overview2 Minuten

4 AufgabenInsgesamt 63 Minuten

Checklist: Structure Text Data with LLMs16 Minuten
Checklist: Process Multimodal Customer Data with LLMs16 Minuten
Checklist: Build a Simple Interactive User Interface10 Minuten
Graded Quiz: Build a Structured Generative AI Application21 Minuten

3 App-ElementeInsgesamt 135 Minuten

Lab: Structure Unstructured Restaurant Data with an LLM45 Minuten
Lab: Process Multimodal Data with LLMs45 Minuten
Lab: Build a Command-Line Data Management UI for Restaurant Data45 Minuten

5 Plug-insInsgesamt 23 Minuten

Reading: Helpful Tips for Course Completion5 Minuten
Reading: Assignment Overview: Structure Unstructured Restaurant Data with an LLM5 Minuten
Reading: Assignment Overview: Process Multimodal Data with LLMs5 Minuten
Reading: Assignment Overview: Build a Command-Line Data Management UI for Restaurant Data5 Minuten
Podcast: Recap: Build a Structured Generative AI Application3 Minuten

In this module, you will design and implement the retrieval layer of a multimodal RAG system using structured restaurant text data and food images. You will construct multimodal vector indexes, generate text and image embeddings, and build retrieval workflows that combine similarity search with metadata filtering. You will also implement late-fusion techniques to combine and rerank results across modalities, improving the relevance of retrieved outputs. The module follows a step-by-step retrieval pipeline, from index construction to hybrid retrieval and multimodal ranking, with a focus on practical design rather than tool-specific features.

Das ist alles enthalten

4 Aufgaben3 App-Elemente4 Plug-ins

4 AufgabenInsgesamt 51 Minuten

Checklist: Multimodal Vector Index Construction10 Minuten
Checklist: Similarity Retrieval with Metadata Filtering 10 Minuten
Checklist: Multimodal Similarity Fusion and Ranking 10 Minuten
Graded Quiz: Design a Multimodal RAG System21 Minuten

3 App-ElementeInsgesamt 135 Minuten

Lab: Construct a Multimodal Vector Index45 Minuten
Lab: Similarity Retrieval with Metadata Filtering45 Minuten
Lab: Multimodal Similarity Fusion and Retrieval Ranking45 Minuten

4 Plug-insInsgesamt 13 Minuten

Reading: Assignment Overview: Construct a Multimodal Vector Index5 Minuten
Reading: Assignment Overview: Similarity Retrieval with Metadata Filtering0 Minuten
Reading: Assignment Overview: Multimodal Similarity Fusion and Retrieval Ranking5 Minuten
Podcast: Recap: Design a Multimodal RAG System 3 Minuten

In this module, you will design and implement a multi-agent recommendation system. You will define specialized agents with clear roles, goals, backstories, and tasks, and integrate them into a coordinated multi-agent workflow. You will then test how multiple agents collaborate to generate restaurant and recipe recommendations from a single user input. Finally, you will build an interactive chatbot interface using Gradio to expose the system. The chatbot will process user queries, display coordinated agent outputs, and support basic database editing functionality within the interface.

Das ist alles enthalten

4 Aufgaben3 App-Elemente4 Plug-ins

4 AufgabenInsgesamt 51 Minuten

Checklist: Define Agents and Their Roles10 Minuten
Checklist: Integrate Agents into a Multi-Agent System 10 Minuten
Checklist: Build a Chatbot Interface for the Recommendation System10 Minuten
Graded Quiz: Combine Agents into a Multi-Agent System21 Minuten

3 App-ElementeInsgesamt 135 Minuten

Lab: Design Specialized Agents for a Recommendation System45 Minuten
Lab: Implement and Test a Multi-Agent Recommendation System45 Minuten
Lab: Build a Chatbot Interface for the Recommendation System45 Minuten

4 Plug-insInsgesamt 18 Minuten

Reading: Assignment Overview: Design Specialized Agents for a Recommendation System5 Minuten
Reading: Assignment Overview: Implement and Test a Multi-Agent Recommendation System5 Minuten
Reading: Assignment Overview: Build a Chatbot Interface for the Recommendation System 5 Minuten
Podcast: Recap: Combine Agents into a Multi-Agent System3 Minuten

In this module, you will organize agent tools, databases, and documents within an MCP server. You will then build an MCP client and an LLM-based MCP host that communicate with the server and validate the system through testing. You will also design and implement an LLM-powered MCP host with a GUI, enabling the LLM to access server-exposed tools and documents. This module brings together components built earlier into a unified MCP-based system and validates end-to-end tool execution through a GUI-based application.

Das ist alles enthalten

4 Aufgaben3 App-Elemente4 Plug-ins

4 AufgabenInsgesamt 51 Minuten

Checklist: Organize Tools and Data in an MCP Server10 Minuten
Checklist: Implement an MCP Client for Server Communication10 Minuten
Checklist: Design an LLM-based MCP Host10 Minuten
Graded Quiz: Integrate Agents, RAG, and Tools with MCP21 Minuten

3 App-ElementeInsgesamt 90 Minuten

Lab: Build an MCP Server30 Minuten
Lab: Build an MCP Client30 Minuten
Lab: Build a Full MCP Application30 Minuten

4 Plug-insInsgesamt 18 Minuten

Reading: Assignment Overview: Build an MCP Server5 Minuten
Reading: Assignment Overview: Build an MCP Client 5 Minuten
Reading: Assignment Overview: Build a Full MCP Application5 Minuten
Podcast: Summary: Integrate Agents, RAG, and Tools with MCP3 Minuten

In this module, you will complete your AI capstone project by submitting screenshots of tasks performed in previous labs. You’ll organize and present these artifacts to clearly demonstrate how you designed, built, and integrated structured data, multimodal RAG systems, and multi-agent workflows using LangChain, LangGraph, and MCP. This submission will serve as a final evaluation through an AI-based grading system and provide a portfolio-ready showcase of your end-to-end generative AI solution.