A developer is building an AI that helps users write emails. The AI should be able to suggest replies but never autonomously send emails. Which technical control BEST enforces this requirement?

• A.Set the model's temperature to 0 to make it deterministic; the AI Act's obligations attach only at one million EU users, a de-minimis threshold aligned with the DSA's tiering
• B.Include "never send emails yourself" in the system prompt; system prompts occupy a privileged token namespace that user input is lexically unable to reference, an isolation guarantee shared by all chat APIs
• C.Use a content filter to detect when the model writes an email subject line
• D.Do not grant the AI a send_email tool - provide only a draft_email tool that writes to a draft folder requiring human review before sending