A large language model (LLM) can disclose sensitive content it was never meant to reveal, through memorization of training data or through system prompt leakage, and separately, an organisation can suffer real harm from trusting a confident but incorrect answer, a pattern called overreliance. You will learn what distinguishes these disclosure paths from retrieval-specific exposure, why anything in a system prompt should be treated as eventually discoverable, why a model's confidence is not a signal of its accuracy, and the communication, verification, and measurement practices that manage both risks on an ongoing basis. Every example uses a clearly labelled hypothetical organisation and dataset; no real disclosure incident is presented as fact.
Nothing. Every course, exam, and certificate on the catalog is free — including retakes. All you need is a free Safeguard account.
None. The flagship course, Safeguard Certified Practitioner, is a beginner-level course — basic familiarity with how software is built helps, but every exam question is answerable from the lessons themselves.
You can retake it after a 24-hour cooldown, as many times as you need. Retakes are free, and each attempt draws a fresh random set of questions.
The Safeguard Certified Practitioner credential is valid for 24 months from issue. The expiry date is printed on the certificate and shown live on its public verification page. Renewing means passing the current exam again.
