Generative AI and Large Language Models (LLMs) are rapidly transforming how software applications are designed, developed, and deployed. Beyond basic interactions with AI tools, organisations are increasingly exploring how to integrate LLMs into applications, connect them to enterprise data, customize their capabilities, and develop intelligent agents that can perform complex tasks.
This course provides a practical introduction to key techniques and tools for developing LLM-powered applications. Learners will explore prompt and context engineering, LLM integration through APIs and local deployments using tools such as Ollama, Retrieval-Augmented Generation (RAG) and application development with LangChain, fine-tuning, context-aware AI agents, and AI safeguards using Guardrails AI. Through hands-on activities, learners will gain practical experience in building AI-powered solutions while addressing considerations such as accuracy, privacy, security, and responsible deployment.
Learning Outcomes
1. Apply prompt and context engineering, LLM APIs, local models, and RAG techniques to develop AI-powered solutions.
2. Develop AI solutions incorporating fine-tuned LLMs and context-aware AI agents.
3. Evaluate AI solutions based on accuracy, security, performance, and responsible use
Day 1
Morning
- Mastering Prompt and Context Engineering
- Integrating with LLMs via APIs and Local Deployments
Afternoon
- Building Retrieval-Augmented Generation (RAG) Pipelines
- Applying Fine-Tuning Strategies for Custom LLMs
Day 2
Morning
- ngineering Context-Aware Autonomous AI Agents
- Hardening LLM Pipelines with Guardrails AI
Afternoon
- Written Assessment
- Course Feedback