capability
Analysis
#chat
#ai
#repo

Chat with Your Code

Chat with Your Code turns a repository into a queryable knowledge surface. Ask 'where is auth handled?' or 'what does this script do?' and get answers grounded in your actual files.

What it is

Folder-scoped LLM chat with file-citation grounding and per-session persistence.

Why it's useful

Removes the cold-start cost of reading an unfamiliar codebase; pairs nicely with static analysis findings.

How Decoder implements it

Folder-scoped chat sessions persist across logins; answers cite the files used; tone and proficiency hydrate from your profile.

When to use it

Onboarding, code review prep, exploring third-party drops, drafting documentation.

When NOT to use it

Production decisions without verifying the cited code — LLMs still hallucinate.

Practical example

'Where does this app validate uploads?' → Decoder cites the relevant server function and quotes the zip-slip guard.

FAQ

Glossary

Grounding
Anchoring an LLM answer in retrieved source content rather than the model's general knowledge.

Related