Use the full guide below so the model understands Creavax structure.
Build Creavax Templateswith clean, valid JSON
Give this guide to ChatGPT, Claude, Gemini or another AI before asking it to create a Creavax Template. The guide defines the package shape and the critical Agent / Model / Output connection rules.
Give the AI the rules before the idea
Copy or download the guide, send it to the AI, then describe the Template you want. The AI should return only a valid .creavax-template.json package. Paste that JSON into Build with AI and validate it before creating the Draft.
Tell the AI the goal, required inputs and expected final output.
Save or copy the returned package as a .creavax-template.json file.
Build with AI validates the schema, capabilities and workflow before import.
The Agent owns both execution and output
A Model is the execution dependency of an Agent. It must never be wired directly to the final Output. Image/reference inputs connect to the Agent and remain available to that Agent's Model at runtime.
Correct:
Input -> Agent
Agent -> Model
Agent -> Output
Forbidden:
Model -> OutputCopy this into any AI
This is the portable helper prompt. It is intentionally provider-neutral and tells the model to return only the Creavax Template JSON.
You are creating an importable template package for Creavax Template Builder.
Your final answer must be one valid .creavax-template.json document. Do not create application code, React components, Laravel/PHP code, ZIP patches, explanations, or installation steps.
Required root structure:
{
"schema_version": "1.0",
"type": "creavax_template",
"template": { ... }
}
Creavax workflow architecture:
INPUT -> AGENT
AGENT -> MODEL
AGENT -> AGENT
AGENT -> OUTPUT
The Model is an execution dependency of an Agent. The Model is NOT the producer node of the final Template Output.
Correct:
{ "from": "product_scene_creator", "to": "image_model" }
{ "from": "product_scene_creator", "to": "final_image" }
Forbidden:
{ "from": "image_model", "to": "final_image" }
Never connect a Model directly to an Output. Creavax may reject that graph with:
Output must be connected to an Agent, not directly to a Model.
INPUTS
- Every user-configurable value must be an Input.
- Use meaningful unique snake_case keys.
- Typical input types include image, text and select.
- Select inputs should include a valid default and unique label/value options when appropriate.
AGENTS
- Each Agent must have a unique key, name and clear system_prompt.
- The system_prompt should explain how to use inputs, what to preserve, what to generate, the expected result and important restrictions.
- Complex templates may use multiple Agents connected as a directed workflow. Agent -> Agent is supported.
- An upstream Agent's result becomes runtime input for the downstream Agent. Chains and branches are allowed, but Agent cycles/loops are not.
- Each Agent may use up to three Model slots.
- Do not hardcode provider-specific model names unless the user explicitly asks for one.
MODELS
- Define a Model slot by capability requirements, not by provider ID.
- Describe only the inputs, outputs, operations and optional features genuinely required by the Agent.
- Example for image editing:
"requirements": {
"inputs": ["image", "text"],
"outputs": ["image"],
"operations": ["image_edit"],
"features": []
}
IMAGE / REFERENCE INPUTS
- Connect the image Input to the Agent.
- Creavax runtime can pass an Agent's connected image/reference Inputs to that Agent's Model.
- Do not add a visible Image -> Model connection merely to provide the reference image.
OUTPUTS
- Outputs represent final workflow results.
- Every final Output must be connected from the Agent that produces it, never directly from its Model.
CONNECTIONS
Before returning JSON, verify:
1. Every from/to key exists.
2. Every required Input is connected to the Agent that uses it.
3. Every Model is connected from the Agent that owns/uses it.
4. Agent -> Agent connections may be used for multi-step workflows.
5. Every final Output is connected from an Agent.
6. No Model -> Output connection exists.
7. No Agent cycle/loop exists.
8. No duplicate or meaningless connections exist.
9. All keys are unique.
COMMERCE
- seller_markup is supported in template JSON and represents the creator markup percentage.
- Example: "seller_markup": 25
TRANSLATIONS AND SEO
- Include useful English copy and Persian and Arabic translations when appropriate.
- Use template.translations.fa and template.translations.ar for localized title/description.
- Keep internal machine keys untranslated and stable.
- SEO supports title, description and keywords.
- SEO keywords are limited to a maximum of 10 unique items.
- Example: "seo": { "title": "...", "description": "...", "keywords": ["..."] }
DO NOT
- invent or change Creavax Model Capability rules;
- create Curated Mapping or Classification rules;
- create source code or a ZIP;
- return Markdown commentary around the JSON.
FINAL CHECK
- schema_version is "1.0"
- type is "creavax_template"
- template exists
- JSON syntax is valid
- no comments inside JSON
- no trailing commas
- all connection endpoints exist
- INPUT -> AGENT
- AGENT -> MODEL
- AGENT -> AGENT when a multi-step workflow is needed
- AGENT -> OUTPUT
- no Agent cycles
- never MODEL -> OUTPUT
- no more than 10 SEO keywords
Return only the final valid JSON, ready to save as:
template-name.creavax-template.jsonA minimal Product in Scene package
This example shows the correct graph: the product image goes to the Agent, the Agent uses the compatible image-edit Model, and the final image comes from the Agent.
{
"schema_version": "1.0",
"type": "creavax_template",
"template": {
"name": "Product in Scene",
"slug": "product-in-scene",
"category": "Product Photography",
"description": "Turn a simple product photo into a premium commercial advertising scene.",
"seller_markup": 20,
"translations": {
"fa": { "title": "محصول در صحنه", "description": "عکس محصول را به تصویر تبلیغاتی حرفهای تبدیل کنید." },
"ar": { "title": "المنتج داخل المشهد", "description": "حوّل صورة المنتج إلى مشهد إعلاني احترافي." }
},
"seo": {
"title": "Product in Scene AI",
"description": "Create professional product advertising images with AI.",
"keywords": ["product photography", "product ads", "AI image edit"]
},
"inputs": [
{ "key": "product_image", "type": "image", "label": { "en": "Product Image", "fa": "تصویر محصول" }, "required": true },
{ "key": "scene_style", "type": "select", "label": { "en": "Scene Style", "fa": "سبک صحنه" }, "required": true, "default": "auto", "options": [{ "label": "Auto", "value": "auto" }, { "label": "Luxury", "value": "luxury" }] }
],
"agents": [
{ "key": "product_scene_creator", "name": "Product Scene Creator", "system_prompt": "Preserve the product identity and create a professional advertising scene." }
],
"models": [
{ "key": "image_model", "label": "Compatible Image Edit Model", "requirements": { "inputs": ["image", "text"], "outputs": ["image"], "operations": ["image_edit"], "features": [] } }
],
"outputs": [
{ "key": "final_image", "type": "image", "label": "Final Advertising Image" }
],
"connections": [
{ "from": "product_image", "to": "product_scene_creator" },
{ "from": "scene_style", "to": "product_scene_creator" },
{ "from": "product_scene_creator", "to": "image_model" },
{ "from": "product_scene_creator", "to": "final_image" }
]
}
}