Python

AI Engineering Foundations

Python, APIs, HTTP and the engineering craft behind every AI system

Building LLM Applications

Tokens, context windows, prompting, structured outputs and function calling

Production RAG

Build retrieval systems that actually work in production

Building AI Agents

Give LLMs tools, memory and the ability to act autonomously

Agentic Workflows

State machines, graphs, multi-agent systems and MCP

LLM Evaluation

Measure retrieval, generation, agents and production quality

FDE Engineering Fundamentals

Discovery, solution architecture, POCs and productionisation

Build a Production HTTP API

Implement a POST /api/echo endpoint that validates input, returns structured output, and handles errors with proper status codes.

Call an LLM with Structured Output

Implement call_structured() that returns a validated Pydantic model from an LLM, with retry on validation failure.

Document Chunking Strategies

Implement three chunking strategies and measure their impact on a sample retrieval eval.

Embeddings & Vector Search

Implement a VectorStore with embed, insert, and search(filter) methods.

Reranking for Retrieval Precision

Retrieve top-20 with vector search, rerank to top-5, and measure precision@5 improvement.

Build a ReAct Agent Loop

Implement run_agent(task, tools, max_iter) that loops reasoning + tool calling until final answer or max_iter.

Add Tracing & Observability

Instrument call_llm, retrieve and tool_call with spans. Export to a trace backend.

Build an Evaluation Pipeline

Implement run_eval(golden_set, prompt_version) -> Report with faithfulness and answer_relevance scores.

AI Chatbot

Your first production LLM application

Document Summariser

Summarise long documents with chunking and map-reduce

RAG Assistant

Production retrieval-augmented generation over your documents

Research Agent

Autonomous multi-step research with tool calling

Multi-Agent Research Platform

Specialised agents orchestrated to solve complex research

Enterprise Knowledge Assistant

FDE capstone: ship an enterprise AI assistant end-to-end