When an agent gets an answer about your code wrong, the model is rarely the problem. It was handed the wrong code. Retrieval decides what the agent sees, and for code, no single kind of search is enough.
The short answer
AI agents working on code need hybrid search: keyword search for exact identifiers, vector search for meaning, and a code knowledge graph for relationships such as call chains across services. The results are fused into one ranked list, and answers cite where they came from.
Three questions, three failures
Here are three questions an engineer might ask about a payments system, and the search method that fails each one.
| Search methods and the questions they miss | Keyword search | Vector search | Graph traversal |
|---|---|---|---|
“Where is REFUND_LIMIT_EXCEEDED raised?” | Finds it exactly | May return similar errors instead | Needs a starting node |
| “How do we stop refunds above the original amount?” | Misses code without those words | Finds the check by meaning | Needs a starting node |
| “What breaks if I change this function?” | Finds text, not callers | Finds similar code, not callers | Follows calls across services |
Embeddings are good at meaning and bad at exact strings. Keyword search is the reverse. And neither knows that a function in one repository is called by a handler in another. Code is a network, and only a graph sees the network.
Building the three indexes
Parse, do not just chunk
Source files are parsed into their structure (modules, classes, functions, entry points) so chunks follow the code’s own boundaries instead of a fixed number of lines.
Keyword index
Identifiers, error codes, config keys and comments, searchable exactly.
Vector index
Embeddings of each unit of code and its documentation, for questions asked in plain language.
Knowledge graph
Nodes for services, modules, functions and domain entities; edges for calls, imports and data flow, including calls between services.
Fusing the results
Three ranked lists are not useful to an agent. We combine them with reciprocal rank fusion: each result scores by its rank in each list, so something ranked well by two methods beats something ranked first by only one. It needs no tuning of scores across very different systems, which is why it holds up in practice.
The graph then expands the top results. If the search finds the refund check, the graph adds the functions that call it and the service that exposes it, so the agent sees the change in context rather than as an isolated snippet.
Good retrieval does not give the agent more code. It gives it the right neighbors.
Answers that cite their sources
Every passage the agent uses keeps a pointer to its file and lines. When it answers a question or drafts an impact analysis, it cites them. That turns “the agent says so” into something a reviewer can check in seconds, and it makes wrong answers easy to spot.
What we measure
- Recall at k on a fixed set of real questions with known answers: did the right code appear in the top results?
- Citation accuracy: does the cited code actually support the claim?
- Cross-repo hits: for impact questions, did retrieval find the affected services outside the starting repository?
We rerun the set whenever an index, a model or a fusion setting changes, so a retrieval regression shows up before an agent builds on it.
In CrewPE
CrewPE reads your repositories into a knowledge graph with keyword and vector indexes alongside, so specs, impact analysis and answers name every service a change touches.
See how CrewPE worksQuestions teams ask
- What is hybrid search for code?
- Hybrid search combines more than one retrieval method, usually keyword search for exact identifiers, vector search for meaning, and for code a knowledge graph for relationships such as calls and imports. The results are merged into one ranked list.
- Why is vector search not enough for code?
- Embeddings match meaning, so they can miss exact names such as an error code or a config key, and they do not know which functions call each other. Code questions often need both exact matches and relationships.
- What is reciprocal rank fusion?
- A way to merge ranked lists by giving each result a score based on its rank in each list. Results ranked well by several methods rise to the top, without having to compare raw scores from very different search systems.
Sources
Product and pricing details change often. Check each vendor’s own pages before you decide.
Sneha
AI engineer at EnWithAI, working on CrewPE’s retrieval, grounding and agent evaluation.