How We Improved Agentic Search

kept by eddie may 07

Ranking search results to surface definitions before tests and vendor code improves first-query retrieval and helps coding agents find the right files sooner, while raw speed gains alone barely reduce end-to-end runtime.

Fast regex search: indexing text for agent tools
Cursor is building local indexes for regular expression search to reduce agent wait times from 15-second ripgrep runs in large monorepos.
also on ripgrep, #search-engine, #ai-coding, #software-engineering, #developer-tools
The next GitHub is not worth winning — David Poblador i Garcia
The author argues that most development work is ephemeral and should stay local, proposing a staging area where experiments remain on‑device until they merit pushing to GitHub.
also on Entire, #ai-coding, #software-engineering, #developer-tools
How I Rebuilt My Development Workstation for Agentic Work
The author rebuilt their development workstation around terminal-native tools like WezTerm, tmux, and Neovim to support agentic workflows with parallel human-agent collaboration across Git worktrees.
also on ripgrep, #ai-coding, #software-engineering, #developer-tools
Tutorial - Entire
Entire Skills enable AI agents to explain code, investigate changes, search history, and hand off work between sessions.
also on Entire, #ai-coding, #developer-tools