# Guides

> Plain guides for people who use coding agents: the problem first, then where LLMGRAPH fits and what it can't do.

Each guide explains the problem first, then says where LLMGRAPH fits and what it can't do.

- [When your agent says "done" but the code is broken](https://beta.llmgraph.in/guides/agent-says-done-but-code-is-broken.md): Why coding agents call broken code finished, and how to check their work.
- [A Claude Code Stop hook that runs your type checker](https://beta.llmgraph.in/guides/claude-code-stop-hook-type-check.md): A Stop hook tested on Windows (Python v3.12 with pyright) that type-checks changed files.
- [Grep, your language server, or LLMGRAPH?](https://beta.llmgraph.in/guides/grep-language-server-or-llmgraph.md): Which one a coding agent should use for which question.
- [What static analysis can't see, and why your agent should know](https://beta.llmgraph.in/guides/what-static-analysis-cant-see.md): The blind spots every code-reading tool has.

The product documentation starts at the [docs](https://beta.llmgraph.in/docs.md), and short answers are on [questions and answers](https://beta.llmgraph.in/docs/faq.md).