Modules
Take single modules or the whole track. Two hour sessions, combined into half days where it suits your calendar.
Prompting and LLM APIs for Developers
System versus user prompts, streaming and error handling against a real API.
- System versus user prompts in code
- Streaming responses and error handling
- LLM API integration patterns
- Foundations for everything that follows
Building a Custom RAG Application
Embeddings, vector databases and retrieval built into a working app from scratch.
- RAG architecture fundamentals
- Embeddings and vector databases
- Ingestion, embedding and retrieval end to end
- A Streamlit UI for the app
Tool Calling and MCP Integration
Extend an LLM with external functions and wire in the Model Context Protocol.
- Tool calling and function execution
- Model Context Protocol integration
- Agentic and multi-agent patterns
- Memory and state across turns
Shipping AI Features to Production
Scaling, caching, monitoring and the operational realities of running AI features.
- Scaling, caching and monitoring
- Testing LLM integrations
- Deployment and operations
- Architectural best practices for production
Teams Often Pair This With
Related modules other teams add alongside this track.
Structured Outputs and Reliability
Get dependable JSON, Markdown and XML out of a model and manage hallucination.
View module Security and Threat Modelling · Architecting Secure LLM ApplicationsSecure-by-Design for AI Features
Build security into AI features from the start, not bolted on afterwards.
View moduleEnquire About This Training
Tell us which modules interest you and we will propose a plan within 24 hours. Choosing Enquire on a module above fills in the subject for you. Add more than one if you like.