Agents And Tool Use easy
A personal assistant agent should remember user preferences across months of conversations. A teammate proposes appending every past conversation to the prompt. What is the better approach?
- A Keep appending, since a long-context model can attend to every past message equally well.
- B Fine-tune the model nightly on each user's conversations so preferences live in the weights.
- C Store facts in a long-term store and retrieve only the relevant ones into each new request.
- D Summarize all history into one fixed paragraph that is prepended to every system prompt.
Answer: C. Store facts in a long-term store and retrieve only the relevant ones into each new request.
**Memory is a retrieval problem**: storing facts externally and fetching only relevant ones keeps prompts small and focused, at the cost of building and tuning retrieval. Appending everything (A) works only while history is short; past that, cost grows with every request and relevant details get buried. A fixed summary (D) loses detail as history grows.
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?