lesson 06

AI Development

Monocurl scenes are plain text files and LLMs can be quite helpful in avoiding boilerplate / tedious layout tasks.

Current Status

An MCP (Model Context Protocol) server for Monocurl is being built. When complete, it will let AI assistants directly read Monocurl's documentation, stdlib reference, and example scenes as structured resources, making them much better at writing correct code.

In the meantime, the most effective approach is to point the assistant at the right context manually.

Giving An AI Assistant Context

For now, some useful things to share:

The GitHub repository. Point the assistant at https://github.com/monocurl/monocurl or possible https://github.com/monocurl/monocurl/tree/rust/crates/mcp/docs. The stdlib files in assets/std/std/ are the ground truth for constructors, operators, and animations.

Website https://monocurl.com/docs and https://monocurl.com/learn can also be helpful for the AI.

An example scene Copy one of the built-in example scenes (.mcs files) that's most relevant to what you want to build.

Headless Mode

Monocurl will watch for file changes and dynamically update the timeline and viewport in response to any external edits, including those from AI agents. Consequently, you can use your preferred text editor or an AI agent to write the scene source file, then switch back to the Monocurl editor to see the results and scrub through the timeline. If you would prefer to use the left hand space for a terminal instead of the default editor, enable headless menu under the File menu.