Lab: Conditional access for AI agents
Your own Monosign server and a small lab client that plays an AI agent building a nightly report. The agent trades its credential for a short-lived access token, and Monosign decides at that moment whether it may have one. Limit the agent to certain hours and to a network, watch the token request being refused with the reason, read the refusals in the audit trail, and then set restrictions that let the agent work again.
Monosign University Pass 30 minAdvanced DE · EN · ES · TR Administrator Security analyst Architect
Version 1 · updated Nov 10, 2026
Hands-on lab
New
Sign in to start
Included with University Pass.
What you will learn
- Explain how an AI agent gets a short-lived access token for its credential
- Restrict an agent to allowed hours and allowed IP ranges
- Find out from the audit trail why an agent's token request was refused
Lab tasks
Each task is checked automatically against the real state of your lab environment.
- 1. Register the Report Assistant agent and get its first access token
- 2. Allow the agent only at certain hours and see a token request refused
- 3. Allow the agent only from one network and read the refusal in the audit trail
- 4. Set restrictions that fit the agent and get a token again