A security engineer notices that an LLM agent in a research pipeline is making 800 outbound API calls per hour, causing $400 in API fees and hitting rate limits for the team's TI subscription. What design control should have been in place?

• A.Reduce the agent's context window so it processes less information per call
• B.The agent should be given a slower internet connection to rate-limit itself naturally
• C.Agent loop cost guards: a per-task maximum step limit and a per-session API call budget should be enforced by the orchestration layer, halting or escalating the agent when thresholds are reached rather than allowing unbounded tool calls
• D.Add a human approval step before every single tool call to prevent excessive usage