Sign in
Catalog / Hands-on lab

Lab: First steps in AI security

Your own Monosign server and a small lab client that plays an AI agent. Register the agent with an accountable owner, give it one permission, cap it with a request budget and watch Monosign throttle and then suspend it. Then look at the AI apps employees open in their browsers and decide which are sanctioned, tolerated or unsanctioned.

MonosignFree 30 minBeginner DE · EN · ES · TR Administrator Security analyst

Version 2 · updated Nov 10, 2026What changed?

Hands-on lab
New
Sign in to start
AI Security First Steps
AI Security First Steps
Complete this to earn the digital badge.

What you will learn

  • Give an AI agent an accountable owner, its own credential and the least permissions
  • Cap an agent with a request budget and choose between throttling and suspending it
  • Find shadow AI in your organization and set a decision for each app

Your lab environment

YOUR LAB SERVERYour browserManagement and the webterminalManagementAI Security: Agents, AI Appssupport-agentLab client in the web terminal,Support Assistant's keyMonosign APIChecks the key, thepermission and the budgetRegisters, sets the budget,decides200, 429 orrefused
Your lab environment: you govern the agent and the AI apps in Management, and the support-agent client plays the AI agent

Lab tasks

Each task is checked automatically against the real state of your lab environment.

  1. 1. Register and activate the Support Assistant agent with an owner
  2. 2. Give the agent a credential and one API permission, then make its first call
  3. 3. Limit the agent to 3 requests a minute and watch Monosign throttle it
  4. 4. Review the AI apps your people use and decide about three of them
  5. 5. Let the budget suspend the agent on its next breach