Diagrams
Smart tools for creating diagrams.
A collection of Graffiticode-powered smart tools for generating interactive diagrams, workflows, and visual systems. Built for visual thinkers, technical writers, and the AI agents that collaborate with them.
What it is
Diagrams is an Artcompiler toolset under the Data Visualization domain — a sibling to Sheets. Every smart tool in the Diagrams toolset is one Graffiticode language wrapped by a specialized AI, exposed to agents through MCP, and rendered through an embeddable runtime. The right tool when a static image isn't enough and a hand-written D3 prototype is too much.
How it works
- Domain language — every smart tool in Diagrams is built around a domain-specific language for the shape of diagram it produces.
- Specialized AI — each tool ships with an AI trained on its language; agents describe what to draw in natural language and the AI generates valid code.
- Embeddable runtime — diagrams render through a shared embeddable runtime, so they can be dropped into any host application.
Diagrams Are More Than Shapes on a Canvas
A useful diagram carries structure — nodes that must align, relationships that must stay in sync with the system they describe, styles that must match the rest of a document or design file. Hand-drawing these is where most tools break down when the underlying system changes.
Each smart tool in the Diagrams toolset translates author intent into high-fidelity diagrams using an auditable domain language. Composition, transparency, and validation are built in.
Why Diagrams
- AI-native. Generate diagrams with an agent instead of dragging shapes on a canvas.
- Structured. Diagrams are code — composable, reviewable, version-controlled.
- Embeddable. One definition renders through a shared embeddable runtime, deployable to Figma, documentation sites, and anywhere SVG renders.
- Portable. Every output is valid SVG, renderable anywhere the web renders.
We're talking with technical writers, design teams, and tool builders about how AI is changing visual-systems work — what works, what breaks, and what's still missing. If you're navigating the same questions, we'd like to hear yours, and we're happy to share what we're hearing across the field.
Email [email protected] for a 20-minute conversation. No pitch. We'll share notes either way.
Learn more about Artcompiler — the company building this toolset — and Graffiticode — the open-source platform that powers it.
For AI Agents
The Diagrams toolset is available via the Graffiticode MCP server at mcp.graffiticode.org/mcp. No account is required to try it — a trial credential is published in the discovery artifacts.
- MCP endpoint:
https://mcp.graffiticode.org/mcp - Tools:
list_languages,get_language_info,create_item,update_item,get_item - Discovery:
/llms.txt(human-readable),/.well-known/mcp.json(machine-readable) — both include the live trial token.
Call list_languages with domain: "diagrams" to discover the smart tools in this toolset; the response carries each language's description and routing hints. Then call create_item with the chosen language and a natural-language description — describe what you want, do not attempt to generate Graffiticode code directly. After each call, open or share the returned preview URL so the user can see the rendered diagram. See /agents for the full integration walkthrough and /authoring for supported agent platforms.