What problem does it solve? Creating technical diagrams that actually communicate structure and meaning is hard: most generated diagrams end up as uniform boxes-and-arrows that display labels without teaching anything, and there is no way to visually verify the output before delivering it. ## Core Features & Use Cases - Visual argument methodology: Maps each concept to a matching visual pattern (fan-out, convergence, timeline, tree, cycle) so the diagram's structure mirrors the concept's behavior. - Evidence artifacts for technical diagrams: Embeds real code snippets, JSON payloads, and actual event names from specs so diagrams educate rather than just label. - Render-and-validate loop: A Playwright-based pipeline renders the .excalidraw JSON to PNG so the agent can inspect its own output and fix overlaps, clipping, and spacing issues iteratively. - Brand customization: All colors live in a single color-palette.md file that can be swapped to match any brand style. - Use Case: Ask your agent to diagram how a streaming protocol delivers events from backend to frontend; it researches the real event names, builds the JSON section by section, renders it, and fixes layout issues before delivering. ## Quick Start Ask your coding agent to create an Excalidraw diagram showing how your system architecture connects its components.
