67How do you build RAG over a large code repository so an agent can answer questions and edit code?▼hardNewCognitionGitHubAnthropic2 replies◆ premiumSplitting source files every 500 characters slices functions in half and wrecks retrieval. Interviewers want to see you chunk on syntax, retrieve by symbol and dependency, and blend lexical exact-match with semantic search the way code search actually needs.Open full answer →
104Claude Code ships with no codebase index while Cursor trains custom embeddings. Which repo-context strategy do you pick, and when?▼hardNewAnthropicCursor◆ premiumTwo frontier coding agents made opposite bets on the same problem, and both published evidence. Candidates who pick a side on vibes miss what the interviewer wants: the axes that actually decide it, and what each choice costs in staleness, latency, tokens, and infrastructure.Open full answer →