Choose what changes.Protect what should not.
Turn an approved image or video project into a typed template with clear text, number, boolean and media inputs.
Pick the parts that change.The rest stays as you approved it.
A JsonCut template is the same visual project with an intentional public input contract for reuse and automation.
Convert when it becomes useful
Start as a normal project and turn it into a template when you expose the first variable.
Bind only meaningful values
Connect copy, media and numeric properties through focused inspector controls.
Discover inputs before rendering
API and MCP clients can request field definitions, examples and required values.
Made in JsonCut.Open one to see the project behind it.
Every title, clip and caption in these is still a layer. Open the project and change whatever you like.

Hiring Engineer Card
Open this example: Hiring Engineer Card
Crux footwork clinic
Open this example: Crux footwork clinic
Webinar Registration Card
Open this example: Webinar Registration CardIn the details.What you control by hand.
- BindExpose only meaningful decisions
- Bind copy, numbers, booleans, colors and media from the same focused controls used for ordinary editing.
- DefaultsKeep the approved design visible
- Every field has a visual default and can include an example so the template remains understandable before real data arrives.
- ContractDiscover inputs before rendering
- Studio, API and MCP expose labels, types, required fields and example values through one versioned contract.
- PreviewFill and inspect before export
- A dedicated template view connects the input form to the finished image or video and its request representation.
What people make with it.
- Reusable campaign systems
- Self-serve content tools
- Data-driven image and video
Before you start.The questions we hear most.
Do I need editing experience to use it?
No. You can ask the AI Director to make the change for you, and every result stays a normal layer you can adjust by hand later.
Does it remain editable after using AI?
Yes. The assistant changes ordinary project layers and versions, so you can inspect and refine the result.
Can the same result be automated?
Yes. Projects can become typed templates or be rendered through the API and MCP.