Question

A developer is building a feature that asks Claude to classify support tickets and return only a single category word (e.g., 'Billing'). They notice Claude sometimes prepends conversational text like 'Sure, the category is...' before the answer. Using only the Messages API structure, what is an effective technique to make Claude begin its response with the category directly?

Accepted Answer

Add a final message with the role 'assistant' containing a partial response to prefill the start of Claude's answer

Answer

Set temperature to 0 so Claude cannot add any introductory phrasing

Answer

Add a second 'system' message immediately before the assistant turn

Answer

Increase max_tokens so Claude has room to finish the classification cleanly