Diagram Generator
What it does
Generate production-ready Graphviz DOT code to visualize complex systems, hierarchies, or processes. Instead of manual drawing, you can feed the AI a concept or a technical architecture, and it will output a structured graph definition. It is particularly useful when you need a quick, logically sound map of a system that can be rendered instantly in any DOT-compatible viewer. By forcing a compact output format (indexed nodes and single-line delivery), it minimizes token waste and ensures the code is ready for programmatic piping or direct pasting into rendering tools like Viz.js or Graphviz.Use cases
- System Architecture: Mapping out microservices and their dependencies to identify bottlenecks.
- Knowledge Mapping: Visualizing the relationship between complex academic concepts or historical events.
- Workflow Documentation: Creating a technical flowchart of a CI/CD pipeline or a business logic process.
- Data Lineage: Tracking how data flows from a source through various transformations to a destination.
How to use
Provide the AI with a topic and an optional number in brackets[n] to specify the minimum number of nodes required for the diagram. If you omit the number, it defaults to 10.
text
I want you to act as a Graphviz DOT generator, an expert to create meaningful diagrams. The diagram should have at least n nodes (I specify n in my input by writting [n], 10 being the default value) and to be an accurate and complexe representation of the given input. Each node is indexed by a number to reduce the size of the output, should not include any styling, and with layout=neato, overlap=false, node [shape=rectangle] as parameters. The code should be valid, bugless and returned on a single line, without any explanation. Provide a clear and organized diagram, the relationships between the nodes have to make sense for an expert of that input. My first diagram is: "The water cycle [8]".Tips
- Specify Complexity: Use the
[n]parameter to force the AI to decompose a simple topic into more granular sub-components for a more detailed map.
- Combine with Renderers: Copy the resulting single-line code directly into Edotor.net or Graphviz Online for instant visualization.
- Iterate on Logic: If the relationships aren't precise enough, ask the AI to "regenerate the edges to better reflect [specific technical detail]" while maintaining the DOT format.
- Post-Process Styling: Since the prompt removes styling for efficiency, you can add your own
node [color=blue]oredge [style=dashed]globally after the code is generated.
Notes
- No Visuals: The AI outputs code, not an image file; you must have a Graphviz renderer to see the diagram.
- Indexing: Because nodes are indexed by numbers to save space, you will need to refer to the node labels within the code to understand which number corresponds to which entity.