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.
SB
This is a great course, which gives you hands on experience on a large RAG based orchestration and ending with creation and Execution of MCP (Server, Client and Host)
Showing: 9 of 9
This is a great course, which gives you hands on experience on a large RAG based orchestration and ending with creation and Execution of MCP (Server, Client and Host)
Good material, excelent examples in the labs
Thank you!
Good
Nice
This is a great course. As the topic has been evolving a lot the last 2 years, some of the material particularly source code is already a bit out-dated. The programming assignments are very interesting, however they are a bit too easy, as many key implementations are provided. Still altogether a very good experience.
Really poor quality of tasks, documentation, and supplied code templates. They need deep rework/or even redone from scratch. I have a feeling that the entire project code for us was created by removing parts of some original solution (known to the Capstone project authors) and putting placeholders like 'do this/do that' instead. So, lots of time taken just to guess what was the original idea and code, and what author meant by the supplied code structure/tasks. I write code for 20 years, but this is a student level really. Unenrolling the project and cancelling my Coursera subscription. Sorry, guys, this is not the level of IBM. Not worth time spent. WIll try visit this course in 6-12 months in hopes that it is fixed.
The lab for coding assignments is not opening. The browser console shows “failed to start tool” errors. This prevents completing the course, as screenshots from the coding exercises are required.
Some code cells in lab Jupyter notebook can't even run. How am I suppose to obtain the results and screenshots for the final graded quiz if I can't even complete the lab sessions?