Lab · Intermediate · 1h
Lab: Red-team your agent
Attack a support agent with adversarial inputs and confirm each is refused or handed over.
- Claude
- ChatGPT
- Any assistant
- agents
- lab
Inside this lab
- Your support agent with an order-lookup tool is about to see real customers. Before it does, you try to make it misbehave.
- Tasks
- 4
The full lab opens with a membership that covers AI Agent Development.
Sign in if you already subscribe.
Sign in
