AppliedAIPrep logoAppliedAI/Prep
← RAG & Agent System Design / 67
hardCognitionGitHubAnthropic

How do you build RAG over a large code repository so an agent can answer questions and edit code?

Splitting source files every 500 characters cuts functions in half and destroys retrieval. The signal is chunking on syntax, retrieving by symbol and dependency, and combining lexical exact-match with semantic search the way code search actually needs.

Updated Aug 2026 · Grounded in real Applied AI Engineer interview loops and written to a senior-engineer editorial bar.

Splitting source files every 500 characters cuts functions in half and destroys retrieval. The signal is chunking on syntax, retrieving by symbol and dependency, and combining lexical exact-match with semantic search the way code search actually needs.

Unlock the other 750 answers · ₹2,000 / $25Your progress and mastery stay saved · 6 months · one payment · no auto-renew
UP NEXT ON YOUR JOURNEY
Next in this trackHow do you do incremental indexing for a RAG system with constant document churn, without a nightly full rebuild?Next in this trackHow do you verify that an answer's citations actually support its claims (grounding verification)?Next in this trackHow do you measure faithfulness (hallucination rate) in a RAG system, and what makes it hard to score?
DISCUSSION · 0

No comments yet — be the first to share your approach.