Generate with AI
The fastest way to create a Blueprint is to describe what you need in plain language. Leapter’s AI reads your description, generates a structured specification, and builds a complete, executable Blueprint — including inputs, outputs, decision logic, and all the connecting elements.How it works
Step 1: Open the Create Blueprint page
Inside your project, click the + Create Blueprint button in the top-right corner. This opens the creation page with a prompt field in the center.
Step 2: Describe your logic
Type a natural language description of the logic you want to build into the text area. Be as specific as you can — include the conditions, calculations, input values, and expected outputs. For example:Delivery fee calculation: base cost is 1.50 EUR per km, orders above 50 EUR ship free, weekends add a 1.50 EUR surcharge, and premium members get 20% off the final feeIf you’re not sure where to start, click one of the Try: suggestions below the prompt field. These fill in a ready-made description you can use as-is or edit to fit your needs:
- Delivery fee — distance-based pricing with discounts and surcharges
- Credit risk rating — scoring logic based on financial criteria
- Insurance premium — rate calculation with age and coverage factors
- Order routing — conditional routing based on order properties

Step 3: Generate the Blueprint
Click the Generate button. Leapter processes your description through several steps — you’ll see a progress indicator showing the current stage, such as “Writing specification” and “Structuring code”.
Step 4: Review the result
Once generation completes, you land directly in the Blueprint Editor with the Visual view open. Your Blueprint is ready to inspect and run.
- Input parameters — the data your Blueprint needs to run (for example:
cartValue,deliveryDistance,isWeekend,isPremiumMember) - Output parameters — the results your Blueprint returns (for example:
deliveryFee) - Decision nodes — conditional branches that route the flow based on your rules
- Assignment nodes — calculations that compute values
- Call nodes — reusable sub-blueprints for modular logic (when the logic is complex enough)
Tips for better results
- Be specific about conditions. “Orders above 50 EUR ship free” generates better logic than “give discounts on large orders.”
- Name your inputs and outputs. If you mention “the customer’s age” and “the monthly premium”, the AI picks up those as parameter names.
- Include edge cases. Mention what should happen in boundary situations — for example, “if the distance is 0, the fee should be 0.”
- Start simple, then iterate. You can always edit the Blueprint with AI after generation to add more conditions or adjust the logic.
What to do next
After generation, you’ll typically want to:- Test your Blueprint — click the green play button on the Start node to run it with sample inputs and verify the outputs.
- Refine the logic — use inline editing to adjust individual nodes, or AI editing to make broader changes.
- Deploy it — once you’re satisfied, connect your Blueprint via REST API, MCP, or export it as code.