You are building a customer support resolution agent using the Claude Agent SDK. The agent is currently…

Question

You are building a customer support resolution agent using the Claude Agent SDK. The agent is currently escalating simple requests like password resets if the customer uses angry language. How should you fix this escalation logic?

Accepted Answer

B. Implement escalation based on objective criteria such as policy gaps, capability limits, or explicit human requests, rather than customer sentiment.

Answer

A. Lower the sentiment analysis threshold so that the agent only escalates if explicit profanity is detected.

Answer

C. Issue an automatic partial refund to calm the customer down before processing the password reset.

Answer

D. Use a PreToolUse hook to normalize the customer's text input to a neutral tone before Claude processes it.

Question 167