User Agreement

The following general conditions apply to the use of Mindbreeze AI.

Operating Models

Four operating models are available for Mindbreeze AI:

• Public Cloud
• Government Cloud
• Private Cloud
• Hyperscaler Cloud

Depending on the operating model, functionality may vary as described.

Volume Packages (pkg)

Volume packages are required to use the AI functionality of Mindbreeze AI described in the scope of services. The volume consumed is determined on the basis of the cumulative calls per year and the number of indexed objects.

A call comprises a request from a user or a service and the corresponding response from the Mindbreeze AI Insight Service called. If a call triggers further sub-calls, these are also counted as independent calls.

Note: Calls that do not include a Mindbreeze AI Insight Service do not count toward volume consumption.

AI Models

Mindbreeze AI uses pre-trained AI models. Fabasoft does not train AI models.

AI models are integrated via the following APIs:

• openai.v1.chat.completions.create/v1/chat/completions
• openai.v1.audio.transcriptions.create/v1/audio/transcriptions

In the “Public Cloud” and “Government Cloud” operating models, Fabasoft selects the AI models. The following pre-trained AI models are used:

• RedHatAI/Mistral-Small-3.2-24B-Instruct-2506-FP8
• openai/whisper-large-v3-turbo

When using other AI models, functionality and quality may vary.

Embedding Models

Mindbreeze AI uses pre-trained embedding models (ONNX format) optimized for Retrieval-Augmented Generation (RAG). Fabasoft does not train embedding models. Fabasoft selects the models used.

The following pre-trained embedding models are used for the specified scope of services:

• intfloat/multilingual-e5-large
• sentence-transformers/all-MiniLM-L6-v2
• sentence-transformers/multi-qa-mpnet-base-dot-v1

Reranking Models

Mindbreeze AI uses pre-trained reranking models (ONNX format) to improve relevance for Retrieval-Augmented Generation (RAG). Fabasoft does not train reranking models. Fabasoft selects the models used.

The following pre-trained reranking models are used for the specified scope of services:

• cross-encoder/ms-marco-MiniLM-L12-v2
• Alibaba-NLP/gte-multilingual-reranker-base

Access Rights

The access rights defined in the Fabasphere are taken into account by Mindbreeze AI.

Dependence on Data and Context

The information, texts, analyses or recommendations generated by the AI are based on underlying data, whereby completeness, timeliness and accuracy cannot be guaranteed. The quality and informative value of the AI output depends largely on the context and the formulation of the input (prompts).

No Guarantee for Accuracy or Suitability

No guarantee is given that the content provided by the AI is correct, complete, up-to-date or suitable for a specific purpose. The use of AI output is at the user's own risk.

Restriction

Since documents of an encrypted Teamroom can only be decrypted at the workstation, AI functionality is not available for these documents.