Which AI models and providers does amaise use?
amaise uses the following AI services:
Azure OpenAI (Microsoft) — for LLM inference (document classification, metadata extraction, summaries, question answering). Processing is regional:
EU: Switzerland North (processing restricted to EU countries)
US: East US (processing restricted to US regions)
CH: Switzerland North (models strictly limited to Switzerland North)
Microsoft Abuse Monitoring is disabled for all amaise deployments — prompts and completions are not cached or accessed by Microsoft. This is contractually ensured via the Azure OpenAI configuration (data-zone-restricted deployments).
Google AI Services — for OCR processing (optical character recognition).
The processing location per environment is specified in the Data Processing Agreement (DPA) and sub-processor list.
Document images are not stored and not used for training.
The specific model versions are defined and fixed per environment in the infrastructure configuration. The platform is model-agnostic and configuration-driven — no model version is hard-coded in the application code.