AI Integration
Ondeva integrates AI directly into your workflows — allowing you to generate, extract, and analyze data using Large Language Models (LLMs) without needing to wire up external services. AI becomes just another building block in your application logic, enabling personalized automation, rich content generation, and powerful classification.
All AI steps store their results in session variables or table entries, making them immediately usable in downstream logic, queries, and UI components.
Text to Variable
Purpose:
Generates AI-powered text from a prompt and stores the result in a session variable.
Key Options:
Prompt: The input text, question, or command given to the model (can include dynamic variables)
Variable: Name of the variable to store the result
When to Use:
Generate product descriptions or summaries
Rephrase or complete user input
Dynamically fill message templates or notification content
Image to Content Field
Purpose:
Generates an image based on a prompt and saves it into a specific field in a table entry.
Key Options:
Prompt: Describes what the AI should generate
Target Table, Entry ID, Field: Where to store the resulting image
When to Use:
Automatically generate hero or thumbnail images for new content
Create profile avatars or decorative assets from user prompts
Keywords Saved as List
Purpose:
Extracts keywords from a text prompt and stores them as an array of strings in a variable.
Key Options:
Prompt: Text to analyze (e.g., a blog post or support ticket)
Variable: Where the array of keywords will be saved
When to Use:
Tag content for search or filtering
Analyze sentiment topics in support logs or survey data
Text Summarization
Purpose:
Condenses a long input text into a shorter, coherent summary.
Key Options:
Prompt: The original long-form text
Variable: Where the summary is stored
When to Use:
Summarize meeting notes, emails, or documentation
Offer TL;DR versions of user-generated content
Audio to Text
Purpose:
Transcribes an audio file into plain text using AI.
Key Options:
Variable: Name of the session variable holding the audio input
Target Table / Entry / Field: Where to store the transcription result
When to Use:
Process voice submissions (e.g., customer feedback, voice forms)
Extract speech from uploaded interviews or podcast clips
Best practices:
AI prompts support full use of
{parameters_x}and{var_x}references, allowing you to dynamically personalize inputs per user/session.Results can be directly used in downstream steps like
Save EntryorSend Mail.Use Text to Variable before API calls or UI rendering to dynamically generate values based on live context.
Last updated