# Extracting AI rules from an existing codebase

DevFeed: [Extracting AI rules from an existing codebase](<https://devfeed.tech/articles/extracting-ai-rules-from-an-existing-codebase-3637.md>)

Original publisher: [Read original article](<https://laravel.com/blog/extracting-ai-rules-from-an-existing-codebase>)

Author: Pushpak Chhajed

Published: 2026-08-31T17:15:00Z

Content type: article

Language: en

Sources: [Laravel Blog](<https://devfeed.tech/sources/laravel-blog.md>)

Topics: [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-skill](<https://devfeed.tech/tags/agent-skill.md>), [ai](<https://devfeed.tech/tags/ai.md>), [laravel](<https://devfeed.tech/tags/laravel.md>), [laravel-boost](<https://devfeed.tech/tags/laravel-boost.md>), [php](<https://devfeed.tech/tags/php.md>)

## AI overview

Laravel Boost uses an agent skill to examine an existing codebase, collect evidence of project conventions, and propose scoped rules for developer approval. The article contrasts this with an earlier deterministic Artisan-command approach that was harder to scale and could elevate framework defaults into unhelpful rules.

## Source excerpt

How Laravel Boost uses an agent skill to find existing project conventions and record the useful ones as scoped rules.