Generating multiple design options is one of the most valuable steps in early-stage site feasibility analysis. Instead of relying on a single layout, developers and architects can compare several possibilities and understand how different assumptions affect density, efficiency, parking, and overall project feasibility.
Whether you are exploring Zenerate through a free trial or using the platform as part of your regular workflow, AI generation can help you create multiple test fit scenarios quickly during a real estate feasibility study.
Below is a simple step-by-step guide to generating multiple design options for a site using AI.
Step 1: Set Up Your Project Information
Start by creating your project and setting up the basic site information, including your parcel, street sides, setbacks, and key development assumptions.
If you are new to Zenerate or need a refresher, you can review our full project setup guide here.
This includes selecting your parcel, confirming street sides, applying setbacks, and entering key development assumptions. Accurate project setup is important because these inputs shape the buildable area and influence the design options generated by the system.
During a development feasibility study, this step helps ensure that each test fit scenario reflects realistic site constraints.
Step 2: Open the AI Generate Tool
Once your project setup is complete, enter your workspace and open the AI Generate tool.
This is where you can begin creating multiple design iterations based on your selected building type, site conditions, and development goals.
Using AI at this stage allows teams to move faster through early land development analysis and compare options before spending time on manual modeling.
Step 3: Select Your Building Type
Next, choose the building type that best matches your project.
Depending on your workflow, this may include multifamily, mixed-use, or other supported building types.
Choosing the correct building type helps the system generate more relevant design options. For example, a multifamily project may prioritize unit count and efficiency, while a warehouse project may require stronger attention to circulation, loading, and operational layout.
Step 4: Adjust Your Generation Settings
Before generating, review your available settings.
These may include assumptions related to floor count, unit mix, or additional uses depending on the project type. Adjusting these settings allows you to guide the AI toward the type of design options you want to explore.
This step is especially useful during site feasibility analysis because it lets teams test different planning assumptions without starting from scratch.
Step 5: Generate Multiple Design Options
Once your settings are ready, select Generate.
The system will create multiple AI test fit scenarios for your site. Each option may explore a different arrangement, massing strategy, or development approach.
Instead of manually creating one layout at a time, AI generation allows teams to quickly compare several design directions within the same real estate feasibility study.
Step 6: Review and Compare Your Results
After the design options are generated, review each scenario carefully.
Compare key metrics such as:
• Unit count
• Gross floor area
• FAR
• Parking count
• Efficiency Ratio
• Profit Margin
The strongest option is not always the largest. In many development feasibility study workflows, the best scenario is the one that balances density, efficiency, site constraints, and financial potential.
Step 7: Select a Scenario and Begin Editing
Once you identify the design option that best fits your goals, select it and begin editing.
You can refine the layout, adjust building placement, modify program assumptions, or continue testing additional scenarios as needed.
This iterative workflow helps architects and developers move from early AI building design exploration into more detailed feasibility planning.
Why AI Generation Helps Early Feasibility
Traditional early-stage design workflows often require significant time to produce multiple options. With real estate development software built for AI generation, teams can explore more scenarios in less time.
This is especially useful during a real estate feasibility study, where early decisions around density, parking, unit mix, and layout can significantly influence project direction.
By generating multiple test fit options quickly, teams can make better-informed decisions before committing to a single design path.
Explore What Zenerate Can Do
If you would like to discuss how Zenerate could support your feasibility or land development workflow, book a demo below to start the conversation.