Agents And Tool Use easy
Your agent can send emails to customers on behalf of the company. Product wants a safety check before any email goes out. Where should that check live?
- A In the system prompt, instructing the model to double-check every email before sending it.
- B In a second model call where the same agent reviews and approves its own drafted email.
- C In the tool description, warning that send_email is dangerous and should be used rarely.
- D In host code that holds the send_email call until a human or policy check approves it.
Answer: D. In host code that holds the send_email call until a human or policy check approves it.
Sensitive actions need an **approval gate outside the model**, enforced by the host, because a model that was confused or prompt-injected into drafting the email can be equally fooled into approving it (B). The tradeoff is added latency and friction per action. Model self-review is acceptable for low-stakes quality checks, not for irreversible actions like sending email.
One system design question a day, with spaced repetition so the ones you miss come back.
Get the appRelated questions
- You are defining a 'schedule_meeting' tool for an agent. Which schema decision most reduces wrong or malformed calls?
- A model emits three parallel tool calls: `get_inventory`, `get_price`, and `get_shipping`. To cut latency, the host appends each result to the transcript as it arrives and immediately re-invokes the model. Runs start failing with malformed-request errors, and some produce hallucinated shipping costs. What should the host do?
- A team splits a coding agent into planner, coder, tester, and reviewer agents, and each receives the full transcript of the previous agent. The expected quality gains did not appear. Cost tripled, and the reviewer often fixates on approaches that earlier agents abandoned. When is a multi-agent split actually justified?
- A support agent should remember each customer's preferences across months of sessions. The team appends every past session summary to the system prompt. After six months, prompts exceed 80,000 tokens, latency has doubled, and the agent sometimes ships to an address the customer replaced weeks ago. What redesign fixes both problems?
- A teammate proposes splitting a single coding agent into five agents, arguing that more agents means smarter results. When is a multi-agent split actually justified?
- A data-analysis agent runs model-generated Python inside the same container as your API service. That container has database admin credentials in environment variables. A security review flags this as critical. What is the best mitigation?