Level 2 - Applied AI Development

About Course

Applied AI Development is a practical, hands-on course for people ready to move beyond simply using AI tools and begin building with them.

You will learn how modern AI applications are put together using Python, LLM APIs, embeddings, retrieval-augmented generation (RAG), tools and agentic workflows. Rather than focusing on theory alone, each session helps you build towards a working application that can answer questions over documents, automate a useful task or support a real business process.

You will also learn how to make AI applications more reliable through evaluation, safety checks, privacy considerations and simple deployment.

By the end of the course, you will have built and presented your own AI-powered project, with practical foundations in the patterns used to create modern AI products.

This course is ideal for students, professionals, analysts, entrepreneurs and aspiring developers who have completed AI Foundations, or already have a basic understanding of how generative AI works. No prior programming experience is required, although you should be comfortable learning technical concepts and writing simple code.

* Use Python to interact with large language models through APIs
* Build AI applications using prompts, system instructions and structured outputs
* Create semantic search systems using embeddings and vector databases
* Build retrieval-augmented generation (RAG) applications over your own documents
* Connect AI models to external tools, functions and data sources
* Design practical agentic workflows for real-world tasks
* Evaluate AI outputs for quality, reliability, safety and cost
* Deploy a simple AI application and present a complete capstone project

Course Content

Python and the AI builder toolkit
- A focused Python refresher for the whole programme - HTTP, REST, authentication, rate limits and error handling - Colab, local environments, Git and GitHub Practical Build a Python application that sends requests to an AI model and processes the output.

Python and the AI builder toolkit

Building with LLM APIs
- System and user instructions, tokens and context - Temperature and sampling, structured outputs, streaming - Hosted APIs, open-weight models and Hugging Face Practical Build a structured information extraction or classification application.

Embeddings and semantic search
- What embeddings represent, and similarity metrics - Sentence Transformers, FAISS and nearest-neighbour search - Building retrieval directly before reaching for a framework Practical Build a semantic search engine over a real collection of documents.

Retrieval-Augmented Generation (RAG)
- Parsing, chunking, embedding, retrieval and context construction - Citations, retrieval failures and hallucination - Hybrid retrieval, reranking, knowledge graphs and GraphRAG Practical Build a complete RAG application over a real knowledge base.

Tools, function calling and agents
- Tool and function calling, state, memory and agent loops - Building an agent loop yourself, before any framework - LangGraph, stateful workflows and common failure modes Practical Build an AI system that can select and use external tools.

Evaluation, safety and deployment
- Golden datasets, deterministic and semantic evaluation - LLM-as-a-judge; separating retrieval quality from generation quality - Prompt injection, data leakage, guardrails and auditability Practical Deliberately break the RAG or agent system you built, then improve it from the results.

Building an AI Application
- Separating model logic from interfaces; FastAPI - Secrets, logging and error handling - Gradio interfaces, containers and hosting Practical Turn one of your systems into an application someone else can actually use.

Capstone project
- Architecture, model choice, data and retrieval strategy - Evaluation, limitations, risks and deployment approach - Published to GitHub with clear documentation Practical Design and build an end-to-end AI application you can demonstrate and explain.

Student Ratings & Reviews

No Review Yet

Level 2 – Applied AI Development

About Course

What Will You Learn?

Course Content

Python and the AI builder toolkit
- A focused Python refresher for the whole programme - HTTP, REST, authentication, rate limits and error handling - Colab, local environments, Git and GitHub Practical Build a Python application that sends requests to an AI model and processes the output.

Python and the AI builder toolkit

Building with LLM APIs
- System and user instructions, tokens and context - Temperature and sampling, structured outputs, streaming - Hosted APIs, open-weight models and Hugging Face Practical Build a structured information extraction or classification application.

Building with LLM APIs

Embeddings and semantic search
- What embeddings represent, and similarity metrics - Sentence Transformers, FAISS and nearest-neighbour search - Building retrieval directly before reaching for a framework Practical Build a semantic search engine over a real collection of documents.

Embeddings and semantic search

Retrieval-Augmented Generation (RAG)
- Parsing, chunking, embedding, retrieval and context construction - Citations, retrieval failures and hallucination - Hybrid retrieval, reranking, knowledge graphs and GraphRAG Practical Build a complete RAG application over a real knowledge base.

Retrieval-Augmented Generation (RAG)

Tools, function calling and agents
- Tool and function calling, state, memory and agent loops - Building an agent loop yourself, before any framework - LangGraph, stateful workflows and common failure modes Practical Build an AI system that can select and use external tools.

Tools, function calling and agents

Evaluation, safety and deployment

Building an AI Application
- Separating model logic from interfaces; FastAPI - Secrets, logging and error handling - Gradio interfaces, containers and hosting Practical Turn one of your systems into an application someone else can actually use.

Capstone project
- Architecture, model choice, data and retrieval strategy - Evaluation, limitations, risks and deployment approach - Published to GitHub with clear documentation Practical Design and build an end-to-end AI application you can demonstrate and explain.

Capstone project

About Course

What Will You Learn?

Course Content

Python and the AI builder toolkit - A focused Python refresher for the whole programme - HTTP, REST, authentication, rate limits and error handling - Colab, local environments, Git and GitHub Practical Build a Python application that sends requests to an AI model and processes the output.

Python and the AI builder toolkit

Building with LLM APIs - System and user instructions, tokens and context - Temperature and sampling, structured outputs, streaming - Hosted APIs, open-weight models and Hugging Face Practical Build a structured information extraction or classification application.

Building with LLM APIs

Embeddings and semantic search - What embeddings represent, and similarity metrics - Sentence Transformers, FAISS and nearest-neighbour search - Building retrieval directly before reaching for a framework Practical Build a semantic search engine over a real collection of documents.

Embeddings and semantic search

Retrieval-Augmented Generation (RAG) - Parsing, chunking, embedding, retrieval and context construction - Citations, retrieval failures and hallucination - Hybrid retrieval, reranking, knowledge graphs and GraphRAG Practical Build a complete RAG application over a real knowledge base.

Retrieval-Augmented Generation (RAG)

Tools, function calling and agents - Tool and function calling, state, memory and agent loops - Building an agent loop yourself, before any framework - LangGraph, stateful workflows and common failure modes Practical Build an AI system that can select and use external tools.

Tools, function calling and agents

Evaluation, safety and deployment

Building an AI Application - Separating model logic from interfaces; FastAPI - Secrets, logging and error handling - Gradio interfaces, containers and hosting Practical Turn one of your systems into an application someone else can actually use.

Capstone project - Architecture, model choice, data and retrieval strategy - Evaluation, limitations, risks and deployment approach - Published to GitHub with clear documentation Practical Design and build an end-to-end AI application you can demonstrate and explain.

Capstone project

Student Ratings & Reviews

Python and the AI builder toolkit
- A focused Python refresher for the whole programme - HTTP, REST, authentication, rate limits and error handling - Colab, local environments, Git and GitHub Practical Build a Python application that sends requests to an AI model and processes the output.

Building with LLM APIs
- System and user instructions, tokens and context - Temperature and sampling, structured outputs, streaming - Hosted APIs, open-weight models and Hugging Face Practical Build a structured information extraction or classification application.

Embeddings and semantic search
- What embeddings represent, and similarity metrics - Sentence Transformers, FAISS and nearest-neighbour search - Building retrieval directly before reaching for a framework Practical Build a semantic search engine over a real collection of documents.

Retrieval-Augmented Generation (RAG)
- Parsing, chunking, embedding, retrieval and context construction - Citations, retrieval failures and hallucination - Hybrid retrieval, reranking, knowledge graphs and GraphRAG Practical Build a complete RAG application over a real knowledge base.

Tools, function calling and agents
- Tool and function calling, state, memory and agent loops - Building an agent loop yourself, before any framework - LangGraph, stateful workflows and common failure modes Practical Build an AI system that can select and use external tools.

Building an AI Application
- Separating model logic from interfaces; FastAPI - Secrets, logging and error handling - Gradio interfaces, containers and hosting Practical Turn one of your systems into an application someone else can actually use.

Capstone project
- Architecture, model choice, data and retrieval strategy - Evaluation, limitations, risks and deployment approach - Published to GitHub with clear documentation Practical Design and build an end-to-end AI application you can demonstrate and explain.