Developer Tooling
These terms cover the infrastructure that connects LLMs to external tools, data sources, and real-world capabilities. This is the layer where models stop being conversational novelties and start being useful, where they graduate from "impressive party trick" to "tool you'd actually rely on."
| Term | What it is |
|---|---|
| Model Context Protocol (MCP) | An open protocol standardizing how AI applications connect to tools and data |
| AI Agent | A system where an LLM has tools and autonomy to accomplish goals |
| Tool Use (Function Calling) | An LLM's ability to invoke external functions through structured requests |
| Orchestration | Coordinating multiple AI capabilities and models for complex tasks |
| MCP Server | A process that exposes tools and data through the Model Context Protocol |
| Context Generation | Transforming raw data into structured content for an LLM's context window |
| Schema | A formal definition of a data structure, the column headers of your data |
| Caching | Storing results for reuse: crude, effective, endlessly documented |
| Frontmatter | Structured metadata embedded at the top of a Markdown file |