TechPrufer
Get started
Glean
Glean logoGlean · Feature trail

Glean Code Search and Code Writer

3 posts · Jan 2026 – Aug 2026

What this trail covers

Glean's engineering productivity tools continue to evolve with enhanced code search and code writer capabilities. Code search provides deep, permission-aware context from all code repositories, enabling engineers to understand code, explain implementations, generate architecture diagrams, and update documentation with sub-second latency. Code writer facilitates the transition from understanding to implementation by generating pull requests that follow existing patterns, reusing code and tests, and running configured checks. The integration with MCP extends code search to external tools like Claude Code and Cursor, while code writer remains available in native Glean integrations. Usage of code search has been observed to double monthly, indicating strong adoption.

All Glean trails
  1. Can AI actually double developer productivity?This post details how Glean's integration with tools like GitHub Copilot and its own code search capabilities contribute to doubling developer productivity. It quantifies the time savings from code generation tools (approx. 1 hour) and Glean's contextual search and automation features (approx. 1.5 hours), totaling 2.5 hours of reclaimed productive coding time. It emphasizes that the real gains come from removing friction across the entire development workflow, not just accelerating code writing. The post also discusses the qualitative benefits of this productivity boost, such as writing higher-quality code, growing developer skills, creating more innovative products, and building happier teams.
  2. Spend less time searching and more time building with Glean code search and code writerThis post details the integration of Glean's code search with the Model Context Protocol (MCP), enabling it to be used in external tools like Claude Code and Cursor. It also highlights the continued development of the code writer, which generates pull requests based on context from code repositories, including Jira bug summaries. The post emphasizes the sub-second latency of code search and its ability to explain implementations, generate architecture diagrams, and update documentation. It also notes the doubling of code search usage monthly.