CertKeen

Azure AI Fundamentals (AI-901) · Free practice question 11 of 12

Agent-only guardrail intervention points

Foundry guardrails scan for risks at defined intervention points. Which two intervention points apply only to agents and not to model deployments? (Select TWO.)

  1. A.Tool call
  2. B.Output
  3. C.User input
  4. D.Tool response
  5. E.Model training data
Show answer and explanation

Correct answers: A. Tool call · D. Tool response

Why: Guardrails support four intervention points: user input, tool call, tool response and output. Tool call, which covers what an agent proposes to send to a tool, and tool response, which covers what a tool returns to the agent, apply only to agents. User input and output apply to both models and agents, and training data is not a guardrail intervention point.

More free Azure AI Fundamentals (AI-901) questions