Beyond Text Search: Context Engines for C++

Key findings

1. 01On 30 real issues from open-source C and C++ projects, ByteAsk Context ranked a file that needed changing first on 57% of them, against 30% for sgrep, so it was right about twice as often.
2. 02On the same 30 issues, Probe ranked a needed file first on 20% of them; ByteAsk Context, at 57%, was right almost three times as often.
3. 03On 35 real open-source C and C++ issues, Graphify's code-only graph ranked a needed file first on 26% of them, against 83% for ByteAsk Context, more than three times as often.

Abstract

Large language model (LLM) coding agents now fix real issues in real projects, but most of that progress has come in Python and a few other popular languages. C and C++, which still underpin operating systems, browsers, databases and embedded software, have received far less attention, though their large codebases are where agents struggle most to find the code a change needs. In C++, which overload a call reaches, which template is instantiated and which #if branch is compiled all depend on the build, and text search sees none of it. We compare ByteAsk Context, a context engine that understands a codebase the way the project's own build does, with three code search tools, sgrep, Probe and Graphify, giving each the input its own documentation asks for. On real issues from open-source C and C++ projects, ByteAsk Context put a file that needed changing first about twice as often as sgrep (57% vs 30%) and almost three times as often as Probe (57% vs 20%), and more than three times as often as Graphify (83% vs 26%).

Cite this paper

Pratyush Saini, Anirudha Kulkarni and Aman Gupta. Beyond Text Search: Context Engines for C++. ByteAsk Research, preprint, November 2026. byteask.ai/research/context-engines-cpp

@misc{saini2026contextengines,
  title        = {Beyond Text Search: Context Engines for C++},
  author       = {Saini, Pratyush and Kulkarni, Anirudha and Gupta, Aman},
  year         = {2026},
  month        = nov,
  institution  = {ByteAsk Research},
  howpublished = {\url{https://byteask.ai/research/context-engines-cpp}},
  note         = {Preprint. Code and data: \url{https://github.com/ByteAsk/context-engines-cpp}}
}