← All parts

Scaling

Design Deep Research · Part 4
Problem context

Design a deep-research feature on top of a chat assistant. A user asks one hard question, such as "How do the leading solid-state battery designs compare on cost and cycle life?" The system plans an investigation, runs many web searches, and reads dozens of sources. After several minutes and many model and tool calls, it returns a long report with citations.

In scope: accepting the question, planning, searching and fetching sources, reading and compressing them, synthesizing a cited report, and streaming progress to the user. Out of scope: the model-serving layer itself (batching, token streaming, GPU scheduling) and the web crawler's fetch and politeness logic. Both are treated as existing services this design calls.

What a strong answer sounds like

State the decision, connect it to a requirement, and name the tradeoff. Keep the design focused on the workload in the prompt.

Ready for the scaling interview?

The AI interviewer asks about this part of Design Deep Research. The interviewer guides you through topics one by one.