Client documents, treated like client documents.

Data residency & retention

Customer document storage and optical character recognition (OCR) run in Microsoft Azure UK South. Structure and layout analysis runs through the Azure OpenAI EU Data Zone within the EEA.

Azure OpenAI receives relevant full-page images and extracted text for structure and layout analysis in the EU Data Zone. Requests use storage disabled (store=false), so normal Responses API conversation state is not retained. Customer material is not used to train generative models. Microsoft performs automated abuse monitoring. Material flagged by the abuse-monitoring system, or identified as part of a potentially abusive pattern of use, may be stored in a Microsoft-controlled abuse-monitoring store and reviewed by authorised Microsoft staff. Documents and OCR remain in UK South.

Uploaded scans are scheduled for deletion from active storage two hours after upload. Azure Storage lifecycle rules make overdue source and standard extracted-text cache blobs eligible for deletion once they are more than one day old. Microsoft controls the exact lifecycle processing time. Deleted blobs may remain recoverable to authorised administrators for up to seven days under Azure soft delete.

Each workspace chooses how long converted outputs are kept: seven days by default, up to 30 days. They are then deleted automatically.

Wording and training

LexForge does not use customer documents to train any AI model.

LexForge checks the finished document against text read from the source. This confirms that the draft matches that reading. It cannot prove that a poor scan was read correctly, so uncertain words are marked for human review.

Two conversion paths use AI differently. On Reconstruct, the standard path, Azure Document Intelligence OCR supplies every word and AI decides structure and layout only. On Restyle, an experimental path a workspace chooses deliberately, an AI model transcribes the words directly from full-page images, including handwriting, and a second focused AI call may propose a correction to an individual disputed span. A correction is kept only when it exactly matches the independent OCR reading. Restyle wording is therefore AI-transcribed and OCR-corroborated, not OCR-transcribed, and every Restyle draft is held for human review rather than released as accepted.

During house-style setup, AI may suggest labels for a firm's own Word styles using style names and formatting only, never document content. A suggestion takes effect only after a person confirms it.

Automatic scan cleanup

Source scans are placed on the short-retention path as soon as they arrive. The application schedules active-storage deletion, with Azure lifecycle processing and soft-delete recovery described above.

Customer document text is not written to application logs.

Retention your firm controls

Your workspace controls the output-retention window. Downloads can be removed automatically after seven to 30 days, while source scans follow the separate short-retention process.

Billing, email and support metadata may be handled by listed providers under their own data-processing terms.