InterCloud AI
AI that answers from your data,
and keeps it yours.
Your people get answers and finished work faster, without your business data leaving your control. InterCloud AI is part of every product, reads only what the person asking may read, and shows where each answer came from.
How it works
Built into the products, bound by their permissions
Answers from live data
Each question is answered by querying the product the person is in, through the same APIs and permission checks the screens use. The assistant keeps no separate copy of your business data.
Sources with every answer
An answer is shown with the records and queries it came from, so the person can check it before acting on it.
Each person's own permissions
The assistant can read only what the person asking can read in the product. Nothing new is opened up by asking.
Admins decide
Workspace Admins choose which providers and models are available, which assistants exist and who may use them.
Self-hosted models
Self-hosted and on-premise model options are available for organizations whose data cannot leave their network.
Thai and English
The assistant and the AI Avatar work in Thai and English, in writing and by voice.
Enterprise AI privacy
What happens to your prompts and data
This is how InterCloud AI is designed and configured.
- Your data stays in your workspace.
- Prompts and answers are processed to serve the request. They are not used to train public models.
- Where a third-party model provider is used, requests go through InterCloud's servers under contracts that prohibit training on your content.
- Admins control providers, models, assistants and access.
See InterCloud AI on your own questions
A demonstration uses the processes and questions of your organization.