# Core Concepts Learn the key concepts used in Kilo Code | Concept | Description | Video Preview | | -------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- | | **Provider** | Kilo Code provides its own built-in API provider that gives you access to the latest frontier coding models without the need to manage API keys that offers access to frontier models such as: OpenAI (GPT-5), Anthropic (Claude), Google (Gemini), Meta (Llama) etc. | | | **Foundational Models** | Large-scale AI models trained on vast datasets that serve as the base for AI applications. Models like GPT, Claude, LLaMA provide core language understanding and generation capabilities. | | | **Prompt Engineering** | Art and science of crafting effective inputs for AI models to achieve desired outputs. Use enhance button to improve your prompt | | | **Modes** | Within Kilo Code you can choose **Architect** mode to plan and design you software, **Code** mode to write and refactor code, **Ask** to understand your codebase, **Debug** to fix software issues and **Orchestrator** to coordinate tasks accross modes | | | **Codebase Indexing** | Codebase Indexing enables semantic code search across your entire project using AI embeddings. | | | **MCP (Model Context Protocol)** | Standardized protocol for managing context and communication between AI models and external systems. Enables seamless integration with tools, databases, and services. | |