KEY LEARNING OUTCOMES
By the end of the Program, your engineers will be able to architect, develop, and deploy robust, scalable GenAI applications that meet real-world business needs.
-
Understand the evolution of AI: Gain historical perspective on artificial intelligence, including the recent shift from predictive to generative models—and why this transition is accelerating real-world adoption and change.
​
-
Adopt a structured lens on the AI ecosystem: Use a clear framework to explore core components such as machine learning, artificial neural networks, deep learning, and transformer architectures.
​
-
Explore different types of intelligence: Understand distinctions between human and machine intelligence, and examine key learning paradigms—supervised, unsupervised, and reinforcement learning.
​
-
Work effectively with data: Understand the attributes and limitations of data, and how to apply best practices to generate actionable insights.
​
-
Demystify AI "black boxes": Deepen your understanding of machine learning models, neural networks, deep learning techniques, and transformer-based systems.
-
Design and develop complex LLM-based applications: Use the LangChain ecosystem to build sophisticated applications powered by large language models.
​
-
Implement advanced Retrieval-Augmented Generation (RAG): Enhance LLM applications with external and domain-specific knowledge sources using advanced RAG pipelines.
​
-
Monitor and evaluate GenAI systems: Use LangSmith to trace, debug, test, and monitor chains and agents—ensuring performance, reliability, and quality.
​
-
Work with structured data and schemas: Leverage PydanticAI to validate and generate structured inputs and outputs, define tool schemas, and support agent development.
​
-
Build and orchestrate multi-agent systems: Use LangGraph to create collaborative, autonomous agents working together toward sophisticated business goals.
-
Optimise production performance: Assess and refine the efficiency, cost, and latency of GenAI systems deployed in real-world environments.
​
-
Integrate external systems: Connect APIs, databases, and analytics tools to GenAI pipelines to support complex business use cases.
​
-
Understand and apply the Model Context Protocol (MCP): Learn how to use MCP to manage contextual data across complex GenAI systems—enabling modular design, consistent state management, and effective memory handling in agentic applications.
​
-
Engage with societal and ethical implications: Reflect on the broader impact of AI, including its influence on work, ethics, and human-machine dynamics.
​
-
Discuss the future of AI and AGI: Explore current thinking on the future trajectory of artificial intelligence and the prospects of Artificial General Intelligence (AGI).