Sankey Flow Diagram Constructor
Builds a Sankey or flow diagram defining nodes, links, value conservation, and clutter-reduction rules.
Prompt
You are a flow-visualization specialist who designs Sankey diagrams for BI. CONTEXT: The flow data tracks [FLOW_ENTITY] moving from [SOURCE_STAGES] to [TARGET_STAGES] with magnitude [FLOW_VALUE]. The question is [FLOW_QUESTION], such as where users or budget leak between stages. TASK STEPS: 1. Define the nodes, the link directionality, and the value each link carries. 2. Verify value conservation: total inflow equals total outflow per node, and flag leaks. 3. Decide node ordering and whether to allow multi-hop or only adjacent-stage flows. 4. Set rules to merge thin links into an 'Other' band to reduce clutter. 5. Specify color encoding (by source, by target, or by flow health) and tooltip content. OUTPUT FORMAT: Node list, Link table (Source | Target | Value), Conservation Check, Ordering and Merge Rules, and Encoding Spec. CONSTRAINTS: Links below [MIN_LINK_THRESHOLD] of total must be merged; the diagram must conserve value or explicitly show loss nodes; cap visible links at [MAX_LINKS]; avoid crossing-heavy layouts where reordering helps.
How to use this prompt
- 1
Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.
- 2
Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.
- 3
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueForces explicit intermediate reasoning instead of jumping to a conclusion, which improves accuracy on hard tasks.
Learn this techniqueRecommended models
Build on this prompt
Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.
More in Data Visualization & BI Dashboards
Executive KPI Dashboard Blueprint Architect
Designs a single-screen executive KPI dashboard layout with metric hierarchy, chart selection, and drill-down logic.
Chart Type Selection Decision Tree
Reasons step by step from data shape and analytic intent to the optimal chart type with ranked alternatives.
SQL-to-Dashboard Metric Layer Definer
Translates raw tables into a governed semantic metric layer with definitions, grains, and reusable measures.
Dashboard Redesign Critique and Rework
Critiques an existing dashboard against visualization best practices, then prescribes a concrete redesign.