# Best practice for AI codebase context

**URL:** <https://community.interop.io/t/best-practice-for-ai-codebase-context/46>\
**Category:** io.Intelligence\
**Created:** [September 3, 2025, 1:25pm UTC](https://community.interop.io/t/best-practice-for-ai-codebase-context/46 "2025-09-03T13:25:26Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![toni.petrov](https://yyz2.discourse-cdn.com/flex028/user_avatar/community.interop.io/toni.petrov/32/17_2.png) [@toni.petrov](https://community.interop.io/u/toni.petrov)\
**Post date:** [September 3, 2025, 1:25pm UTC](https://community.interop.io/t/best-practice-for-ai-codebase-context/46/1 "2025-09-03T13:25:26Z")

</div>

An ageneric AI coding question:

What have you found to work best for examining a new code base and then creating a file for my assistant it can use without clogging the context too much. So far I’ve tried the vanilla CLI tools functionalities e.g. `/init` Gemini CLI, opencode to explore and understand the code base with mixed results and wonder if there’s a way to supercharge that. Maybe by using something like deep research over the code base (if it’s hosted on GitHub) or set up a full RAG workflow?