Model security
By default, questions are answered by open models running in your own cloud account, reached only from your private network. Whether a use case also uses an outside AI service is decided with you.
Where the work happens, and who sets it.
Processing
By default, questions are answered by open models self-hosted in your cloud account. Whether a use case also uses an outside AI service is decided with you for that use case.
Models
Open model families such as Llama, Mistral, Qwen, Gemma and DeepSeek run in your account. Which models run is decided with you.
The platform
Models, retrieval, agents and monitoring sit inside your account.
Who can reach it
Users reach it only from your private network. There is no public endpoint.
Encryption
Data is encrypted at rest and in transit.
Exalt's management plane
Exalt runs a management plane outside your account. It holds no customer content.
Where the line is.
- Exalt Reserve runs on your cloud provider's infrastructure. The provider's own controls, and your agreement with it, sit outside what Exalt provides.
Put local AI to work
where it matters most.
Bring your own review questions to the consultation. We answer them against this page.