You can create personalized AI actions with theCustom template. When you type the desired AI template description, a template is quickly created accordingly and the necessary prompts are automatically written.
Action Name: Specify a name for the AI action.
Sample Output Data: Determines the format of the sample output that the AI will produce.
JSON: If structured data is expected from artificial intelligence, this option is selected. When this option is used, the expected JSON structure and fields can be predefined, so that the model produces output according to the specified schema.
Text: Used for free text (natural language) output.
User Prompt: Represents input from the user. It specifies what the user wants to ask the AI in this field.
Example:You are an AI template builder assistant working in a low-code development environment.When the user provides a short description of the AI use case they want, your task is to
Analyze the use case to understand the goal of the AI action.
Automatically generate a suitable AI template that includes
Task type (e.g. text generation, classification, summarization, translation, etc.)
Detailed prompt structure with variables (placeholder)
Sample output
Input/output format description
Produce the template in an open, developer-friendly format and make it ready to be embedded in the Kuika AI Actions system.
System Prompt: This is the background instruction to be given to the AI. This field defines how the model should behave (for example: “You are a legal expert.”). In other words, it defines the role of the AI.
Model: You can choose from the following models: DALL-E 3, tts-1, whisper-1, GPT-4, yolov8n, camera, gemini-2.0-flash-lite, gemini-2.0-flash, gemini-2.5 flash image generation, and veo 3.0 fast generate preview. The default model is GPT-4.
You can upload “Image” and “PDF” files with the Gemini-2.0 flash model.
Parameters:
Receipt_text: Used by AI Action to analyze, interpret, or convert text into structured data.
Gemini File Parameter: Used to provide file-based input. When “Allow file upload” is active, an image or file can be uploaded from a device and this file is sent to the model in Binary (Bytea) format. When inactive, only text-based (String) parameters are used.
Unknown: Unknown or undefined data type.
Boolean: True/false value.
Bytea: Binary data (e.g. image, file, etc.).
Byte: Integer value between 0-255.
DateTimeOffset: Date and time information.
Decimal: Decimal number.
Double: Larger decimal number.
Guid: Unique identification (UUID).
Int16: Small integer value.
Int32: Medium integer.
Int64: Large integer.
Single: Small decimal number.
String: Text (text) value.
AI Features:
Temperature: Determine the productivity of the AI (0 = consistent, 1 = random responses).
Maximum Length: Set the length of the content generated by artificial intelligence on a token basis.
Stop Sequences: Add a word or sequence of words that will cause the response to stop at a certain point.
Top P: Controls the breadth of the word pool the model will use when generating output. Takes a value between 0 and 1. Low values ensure the model selects only from the most probable and logical words; high values allow selection from a broader and more varied word pool.
Frequency Penalty: Used to reduce repetitive words.
Presence Penalty: Encourages the creation of new content.
Reset to Defaults: Restores the action to its original parameters after changes have been made.
Finally, click on the CREATE button in the top right corner and create your AI action.
