Topics

AI Engineering Topics

Each topic hub organises our tutorials, architectures, challenges and projects into a structured learning path. Start with the fundamentals and progress to production.

RAG

RAG — Retrieval Augmented Generation

Ground LLMs in your private data with retrieval, reranking and citations.

5 tutorials·2 architectures·2 challenges

Vector Databases

Store and search embeddings at scale for semantic retrieval.

2 tutorials·1 architectures·1 challenges

Embeddings

Vector representations of meaning for semantic search and RAG.

2 tutorials·1 architectures·0 challenges

Agents

AI Agents

Build autonomous systems that reason, act and use tools.

4 tutorials·3 architectures·2 challenges

Function Calling & Tool Use

Give LLMs the ability to invoke functions and use tools.

2 tutorials·1 architectures·1 challenges

MCP — Model Context Protocol

The open standard for connecting agents to tool ecosystems.

1 tutorials·1 architectures·0 challenges

Evaluation

LLM Evaluation

Measure retrieval, generation and agent quality. Catch regressions before users do.

3 tutorials·1 architectures·1 challenges

LLM Engineering

Prompt Engineering

Design reliable LLM inputs for structured, grounded outputs.

3 tutorials·1 architectures·1 challenges

Context Engineering

Manage what goes into the context window for quality, cost and security.

1 tutorials·1 architectures·0 challenges

Fine-Tuning

LoRA, QLoRA and when to customise model weights vs RAG.

1 tutorials·0 architectures·0 challenges

Multimodal AI

Vision, audio and image generation for cross-modal systems.

3 tutorials·0 architectures·1 challenges

Production

LLM Observability

Tracing, metrics and debugging for production AI systems.

2 tutorials·1 architectures·1 challenges

Guardrails & AI Safety

Input/output guards, prompt injection defence and content moderation.

2 tutorials·1 architectures·1 challenges