Grep beats LSP? Why coding agents ignore your fancier tools
A study comparing grep and LSP-backed semantic navigation suggests that coding agents often prefer simpler lexical search tools. The author argues that 'LLM-friendliness'—how easily a model can parse and utilize tool output—is a critical factor in agent performance.
Why it matters
Understanding how AI agents interact with development tools is crucial for improving the efficiency and reliability of automated coding assistants.
Star 952 Get started All posts Engineering 9 min read Grep beats LSP? Why coding agents ignore your fancier tools I compared grep with LSP-backed semantic navigation across code-finding and editing tasks. The results show why a tool's LLM-friendliness may matter as much as the capability behind it.
Copy link Why would a coding agent ignore a retrieval interface that returns more precise results?
I explored this question in a small study comparing lexical search with grep against LSP-backed semantic navigation. I expected semantic navigation to reduce noise and save tokens. Instead, agents often stayed with grep . When I forced them to use the semantic path first, task success sometimes fell.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in