Use of AI in Handbooks

Simployer is offering AI search and summary capabilities in our digital handbooks platform. It makes interacting with written routines and processes easier and more natural as end users can write questions and get answers based on the companys own written routines and processes stored in the digital handbooks.  

The information the chatbot is basing its answers from, is the content in the Customers own handbook – which is also the limitation. It will not index, process or use information outside the contents of your handbooks.  

Where is the information used and stored?

All customer data is stored in the same database as the Handbooks content. In addition, vectorized data (anonymized, non customer data) is stored in a dedicated vector database. Data is hosted within the framework of existing subcontractor relationships with Microsoft and Google, in Europe, and under established guidelines regarding security and GDPR compliance. The information used by the AI functionality is the content of the Handbooks and the prompts input by the end users of the Handbooks. Data is not mixed between customers. 

Read more about the Simployer sub-processors.

Which APIs does the search engine utilize?

Simployer uses Artificial Intelligence (AI) only for assistive, non-decisional purposes across selected modules of the platform. AI functionality is designed to support users with information retrieval, summarisation, insights and suggestions — never to make, determine or automate HR decisions. All outputs require human review and validation by the customer.

AI processing is performed using enterprise-grade large language models hosted exclusively within the EU/EEA on the infrastructure of our cloud sub-processors (currently Microsoft Azure OpenAI Services and Google Cloud Vertex AI). Vector storage is provided by Qdrant (EU-hosted). The selection between providers is made by Simployer for resilience, redundancy and model-availability. Provider selection does not change the categories of personal data processed, the legal basis, the purposes, the location of processing, or the contractual protections in place.

No customer data is used to train, fine-tune or otherwise modify the underlying models.

AI features operate on data already processed within each module under the customer’s instructions, and only to the extent necessary to support the specific feature.

The AI processing described below forms part of the customer’s existing legal basis for HR management under GDPR and does not introduce new categories of processing.

How is the data classified?

The data is broadly classified as customer data, ensuring that the Customer retains ownership and all rights to the data, in accordance with existing agreements, including the data processing agreement.

Data is not used to improve language models or for any other AI-related analysis. However, functionality is available for end-users to provide "thumbs up or thumbs down" feedback on the responses. This feedback is used solely by Simployer for statistical purposes to improve the solution.