AI Native Product Engineering

Explain foundation-model behaviour — tokenization, context windows, sampling, cost — and characteristic failure modes such as confabulation and prompt injection.

C2 Understand

Apply prompt, context and retrieval (RAG) engineering, including structured outputs and tool calling, to build LLM features on a cloud AI platform or open-weight stack.

C3 Apply

Design an AI-native system architecture — retrieval, agents, tools, memory and guardrails — through an AI-DLC gated workflow from Inception to Construction.

C6 Create

Evaluate AI systems with golden sets, calibrated LLM-as-judge, cost/latency metrics and CI regression gates, and justify engineering decisions with evidence.

C5 Evaluate

Assess security, privacy and responsible-AI risks using the OWASP LLM and Agentic Top 10, NIST AI 600-1 and EU AI Act risk tiers, and implement proportionate mitigations.

C5 Evaluate · A4 Organise (values)

Collaborate in a team to ship, operate and present an AI-native product with runbook, AI-use log and individual oral defence.

C3 Apply · P4 Mechanism · A3 Value