Resources for turning professional knowledge into AI-powered work
Start with your real goal, understand the skill, inspect what a credible project looks like, and then choose the course that develops the capability.
Choose the question you are trying to answer
These guides are deliberately broad enough to be useful and specific enough to lead to a real build. They are not keyword-variation pages.
Understand the capability
Each skill guide connects a definition to portfolio evidence, professional application, and the relevant curriculum.
AI automation
AI automation combines repeatable workflow logic with model-based steps such as classification, extraction, synthesis, or drafting.
AI agents
An AI agent is a system that uses a model to choose and execute actions toward a goal within defined tools, context, constraints, and oversight.
Retrieval-augmented generation (RAG)
RAG retrieves relevant source material at request time and gives it to a generative model so an answer can be grounded in selected evidence.
AI and LLM testing
AI testing evaluates probabilistic outputs for qualities such as faithfulness, relevance, safety, robustness, fairness, and task success.
AI security
AI security protects model-enabled applications from risks including prompt injection, unsafe tool use, data leakage, poisoned retrieval, and excessive permissions.
MLOps
MLOps applies software delivery and operational discipline to data, model training, deployment, monitoring, and retraining.
AI product management
AI product management defines valuable, feasible, and responsible products when core behaviour is probabilistic rather than fully deterministic.
Data science with AI
Data science uses data preparation, analysis, statistics, and machine learning to produce evidence, predictions, and decision support; generative AI can add natural-language or document capabilities where appropriate.