Agents And Tool Use easy
Users report that an agent occasionally books the wrong meeting room, but you cannot reproduce it. What should you have in place to debug this?
- A Traces recording every step: model inputs, tool calls, arguments, results, and outputs.
- B A log of only the final answer for each run, since that is what users actually see.
- C Aggregate dashboards of average latency and token usage per agent run over the week.
- D A lower temperature setting so every run is deterministic and the bug reproduces locally.
Answer: A. Traces recording every step: model inputs, tool calls, arguments, results, and outputs.
**Step-level traces** are the debugging surface for agents: they show which tool got which arguments and what result led to the wrong booking. The tradeoff is storage cost and handling sensitive data in logs. Lowering temperature (D) does not make runs reproducible when tool results and external state differ between runs.
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?