An advanced course for platform and DevOps teams on governing AI agents as principals: the Model Context Protocol internals that matter for control, the threat model of agent tool traffic, and how Safeguard's agent identity (GA) and MCP Guardrail proxy URLs (early access) bound what agents can do and record what they did. You will design least-privilege agent identities, write per-identity tool policies with argument constraints, rate limits and approval, vet and pin third-party MCP servers, operate the audit and event pipeline across SaaS, VPC, on-prem and air-gapped deployments, respond to agent incidents, and roll the program out with metrics mapped to NIST AI RMF, ISO/IEC 42001 and SOC 2.
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.