Agents And Tool Use easy
A procurement agent needs manager approval before placing orders over a threshold, and managers typically respond within 10 to 60 minutes. How should the agent loop handle the wait?
- A Block the worker thread in a polling loop until the manager clicks approve or reject.
- B Persist the run state, suspend the loop, and resume it when the approval event arrives.
- C Let the model place the order now and send the manager a notice to reverse it if needed.
- D Hold the HTTP request open with a long timeout so the agent can continue in place.
Answer: B. Persist the run state, suspend the loop, and resume it when the approval event arrives.
Human approval takes minutes, so the loop must **suspend and resume** from durable state rather than tie up a worker. The tradeoff is the complexity of serializing the transcript and handling resume events. Blocking (A) works for sub-second automated checks but exhausts workers and loses state on restart at human timescales.
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?