An AppSec course on defending production LLM applications and agents against prompt injection, data egress and unsafe outputs using Safeguard's AI Gateway runtime guardrail proxy (early access) together with MCP Guardrail, agent identity and the platform's policy, gate and evidence layers. You will learn the trust boundaries of LLM applications, the classes of injection and why filters alone fail, how to deploy the gateway in monitor mode and move to enforcement category by category, how to protect outputs and tool-using agents, and how to operate, test and evidence the program against the OWASP LLM Top 10, EU AI Act, ISO/IEC 42001 and NIST AI RMF.
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.
