Modules
Take single modules or the whole track. Two hour sessions, combined into half days where it suits your calendar.
How LLMs Work for Builders
The mental model developers need: capabilities, context windows and model choice.
- Model capabilities and hard limitations
- Context windows and what fits in them
- Choosing the right model for a task
- Ethical and cost considerations up front
Core Prompting Techniques
Context engineering, structured prompts and the system-versus-user distinction.
- Context engineering and structured prompting
- System prompts versus user prompts
- Using personas effectively
- Specificity, output format and iteration
Advanced Prompting Strategies
Chain of thought, few-shot, self-criticism and prompt chaining for harder problems.
- Chain of thought and decomposition
- Zero-shot and few-shot patterns
- Self-criticism and prompt chaining
- Combining strategies for complex tasks
Structured Outputs and Reliability
Get dependable JSON, Markdown and XML out of a model and manage hallucination.
- Producing reliable JSON, Markdown and XML
- Managing and reducing hallucinations
- Domain-specific prompting patterns
- Where prompting ends and real engineering begins
Teams Often Pair This With
Related modules other teams add alongside this track.
Enquire 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.