Cody is an AI coding assistant that uses the latest large language models and codebase context to help developers understand, write, and fix code faster. It connects to Sourcegraph's advanced Search API to pull context from both local and remote codebases, enabling accurate and context-aware assistance across entire repositories.

The assistant is available as an extension for VS Code, JetBrains, and Visual Studio, as well as a web-based interface and a command-line tool. Developers can interact with Cody through a chat interface, use auto-edit suggestions that respond to cursor movements and recent edits, and apply customizable prompts to automate repetitive coding tasks.

Cody supports deep contextual understanding by referencing files, symbols, usage patterns, and APIs across a codebase using the @ mention system. Context Filters allow teams to exclude specific repositories from chat and autocomplete results, giving organizations control over what codebase data informs Cody's responses.

For enterprises, Cody is integrated with Sourcegraph's broader platform, which includes Code Search, Batch Changes, and Code Insights. Sourcegraph Partner LLMs apply zero-retention policies on inputs and outputs, and enterprise subscriptions include full IP indemnification for AI-generated code.