Step-by-Step
Sign up and create a project
Go to app.workshop.ai and create an account.Click New Project and give it a name. You’ll be asked to choose a starting template:
- HTML + Python — The default. Best for dashboards, data apps, and interactive tools. Gives you a Python backend with an HTML frontend.
- Streamlit — A Python-native framework for data apps. Great if you want charts, tables, and interactivity with minimal frontend code.
- Blank (None) — Start with an empty project. Choose this if you have something specific in mind or want full control.
Describe what you want to build
Workshop starts in Plan Mode. Describe your idea in plain language:Workshop will ask clarifying questions about scope, features, and design. Answer them conversationally — this is how it builds a structured plan before writing any code.When the plan looks right, follow the prompt to switch to Build Mode.
Add your data
You can bring data into your project in several ways:
- File upload — Drag a CSV, Excel, or JSON file directly into the chat
- Google Sheets — Share a link and Workshop will read it
- Connectors — Connect to PostgreSQL, MySQL, BigQuery, Snowflake, Supabase, and more through the Connectors panel
Iterate on the result
As Workshop builds, the preview pane on the right shows your app updating in real time. Interact with it — click buttons, test filters, hover over charts.When you want changes, describe them naturally:Workshop updates the code and the preview refreshes automatically.
Tips for Better Results
Be specific about what you want
Be specific about what you want
Build incrementally
Build incrementally
Start with the core functionality, then layer on features:
- “Load the data and show it in a table”
- “Add a chart of sales by month”
- “Add filters for product category and date range”
- “Style it to match our brand colors”
Reference what you see in the preview
Reference what you see in the preview
What You Can Build
Workshop Cloud excels at:- Dashboards — Sales, marketing, operations, KPI tracking
- Data explorers — Let teams filter and explore datasets interactively
- Internal tools — Admin panels, data entry forms, approval workflows
- Interactive reports — Reports with drill-down, charts, and export
- Prototypes — Test ideas with real data before committing to a full build
Sandbox Environment
Your project runs in a managed cloud sandbox with:- Up to 4 CPU cores and 16 GB RAM
- 2-hour active session timeout (sessions restart automatically when you return)
- 10-minute idle timeout
- Pre-installed Python environment with package management
Workshop Cloud currently supports HTML + Python and Streamlit projects. If you need a different tech stack, framework, or access to your local file system, use Workshop Desktop.
Next Steps
- Connect your data sources with Connectors
- Learn Plan and Build modes in Core Concepts
- Read prompting tips in the Prompting Guide
- Join the community on Discord