This Specialization provides a structured pathway for building intelligent AI systems that move beyond text generation to grounded reasoning and action. Beginning with foundational concepts, learners explore how deep learning enables modern text analysis and understand the role of transformers and large language models (LLMs) as the core engine behind today’s AI systems.
The second course advances into applied system design by introducing retrieval-augmented generation (RAG) and knowledge graphs. Learners develop techniques to connect language models with external data sources, improving factual accuracy and contextual understanding. Topics include building retrieval pipelines, extending agents with advanced RAG strategies, and integrating structured knowledge for richer reasoning.
In the final course, learners focus on designing and orchestrating intelligent AI agents. This includes creating single- and multi-agent systems, incorporating planning and tool use, and building complete AI agent applications. The progression equips learners to integrate LLMs, retrieval systems, and knowledge structures into cohesive solutions that address complex, real-world challenges with improved reliability and depth.
This specialization is based on the book Building AI Agents with LLMs, RAG, and Knowledge Graphs written by Salvatore Raieli and Gabriele Iuculano.
Applied Learning Project
Learners engage with structured activities designed to reinforce key concepts across LLMs, retrieval-augmented generation, and knowledge graphs. These exercises support the practical application of techniques such as connecting models to external data and enhancing reasoning with structured knowledge. Through guided analysis and iterative practice, participants build competence in integrating core components into cohesive AI systems.
