Generation and context
Next-token prediction, probabilistic output, and context as the condition under which generation occurs.
AI fundamentals
Why do the observed outcomes occur?
Fundamentals connect each experiment to an accessible conceptual explanation and a demonstrable caveat, without turning the course into product training.
Model behaviour and variability
Tokens, tokenisation, attention, sampling, parameters, repeated runs, and observable variability.
Grounding and evidence
Embeddings, retrieval, source selection, context insertion, claim support, provenance, and bias.
Process and co-construction
Decomposition, intermediate artefacts, roles, handoffs, checkpoints, and process state.
Critique and verification
Conditions of satisfaction, LLM-as-judge, separated judging sessions, revision decisions, and verification.
Decision support and legitimacy
The difference between fluent generation and legitimate decision support, including calibrated reliance and substantive oversight.
Agentic workflows
Perception, reasoning, planning, capabilities, workflow state, validation, permissions, and control points.
Security and trust boundaries
Instruction/data boundaries, prompt injection, source trust, least privilege, validation, approval, auditability, and residual risk.