Securing AI at Work: Practitioner
Set up and run AI tools, connectors and agents securely in real work
AI tools now read your email, open your files, browse the web and act in your other apps. This course from the Enterprise Technology Association (ETA) shows you how to set them up and use them securely in real work: vetting a tool before you rely on it, controlling what data and connections it gets, handling prompt injection and risky AI output in practice, defending your processes against AI-powered fraud and running agents with guardrails, logs and an off switch.
What you'll learn
- How to evaluate an AI tool's data terms, admin controls and security before you use it for work
- How to handle data, files, memory and chat sharing safely in AI tools
- How to grant connectors and integrations with least privilege, and spot consent phishing
- How to recognize and contain prompt injection in email, documents, web pages and knowledge bases
- How to review AI-generated code, links and files, and defend processes against deepfakes and synthetic identities
- How to design, monitor and report on agents using the ETA Agent Autonomy Ladder
Who it's for
People who've finished Securing AI at Work: Foundations (or know GUARD and the Agent Autonomy Ladder) and now set up AI tools, connectors or agents for themselves or a team: team leads, operations and IT generalists, analysts and power users.
How it works
Three modules with a hands-on Try it exercise in every lesson, a knowledge check at the end of each module and a final assessment with short written answers. Score 80% or higher on the final assessment to complete the course (2 credit hours). This course and Cyber Fluency: Practitioner make up Level 2: Practitioner of the ETA Certified Cyber Fluent Professional.
This course teaches good security practice. It is not legal advice, and your organization's AI and security policies always come first.