Document Intelligence

The Problem: Personal Data in Every Document

Enterprises want to process documents with AI - analyze contracts, classify invoices, query policies. But every document contains personal data: names, salaries, social security numbers, addresses, bank details, signatures.

Sending this data to a language model - even a self-hosted one - without protection violates GDPR principles of data minimization. Employee governance agreements restrict processing of employee data. Trade secrets in contracts must not reach third parties.

Current approaches fall short: Manual redaction in Adobe Acrobat is time-consuming, error-prone, and often only cosmetic - the text remains accessible beneath the black bars. Alternatively, avoiding AI processing for sensitive documents eliminates most of the productivity gain.

Roundtrip Pseudonymization for LLM Input

Most PII tools on the market perform one-way redaction - they remove data. For processing with language models, that is insufficient. When an agent needs to analyze a contract, it requires context: "Employee X has salary Y at location Z." Without this context, the model cannot produce a meaningful assessment.

The Gosign approach is roundtrip pseudonymization: names and identifiers are replaced with pseudonyms before the model, the model processes the document, and the real data are re-inserted in the result. The model sees pseudonyms instead of names. The result contains the real data.

┌─────────────┐     ┌──────────────────┐     ┌─────────────┐     ┌──────────────────┐     ┌─────────────┐
│  Document   │     │  PII Detection   │     │  Pseudonym-  │     │  Language Model  │     │  Re-Mapping │
│  (Original) │────▶│  & Classifi-     │────▶│  ization     │────▶│  works with      │────▶│  Pseudonyms │
│             │     │  cation          │     │              │     │  pseudonyms      │     │  → real data│
└─────────────┘     └──────────────────┘     └──────────────┘     └──────────────────┘     └─────────────┘
│                        │                                            │
▼                        ▼                                            ▼
┌──────────────┐         ┌──────────────┐                              ┌──────────────┐
│  Decision    │         │  Mapping     │                              │  Result      │
│  Layer:      │         │  Table       │◀─────────────────────────────│  with real   │
│  What gets   │         │  (stays      │   Reverse mapping           │  data        │
│  replaced    │         │  local)      │                              └──────────────┘
└──────────────┘         └──────────────┘

Decision Steps in the PII Process

The mapping table (pseudonym → real data) never leaves the pre-processing layer. It is deleted after processing is complete - or retained for a defined period, depending on configuration. The language model sees pseudonyms instead of names and identifiers.

Pseudonymization replaces identifiers, not the content. What the text itself reveals about a person stays in place: the role in a small team, a rare diagnosis, a specific incident. Pseudonymized data therefore remain personal data as long as the person can be re-identified with reasonable effort (Recital 26 GDPR). Roundtrip pseudonymization is data minimization, not a legal basis: processing still requires a data processing agreement and, for professional secrecy holders, the chain of obligations under Section 203 of the German Criminal Code (why that is). And it has a price: where a task needs the real names, such as a letter or a draft contract, the model works less reliably with placeholders.

Signature Detection: Find, Verify, Document

Contract management, audit preparation, compliance reviews - all require regular verification: Is this document signed? Where is the signature? Is a countersignature missing? With 5,000 contracts in the archive, manual checking is not feasible.

Signature Detection - Finding Signatures

The Document Agent detects signature fields and present signatures in scanned documents and PDFs. Computer vision, not a language model - specialized ML models for image analysis. The output is structured: page, position, confidence that a signature is present.

Bulk archive verification: "Which of the 5,000 contracts are missing a countersignature?" - Results in minutes instead of weeks.

Onboarding quality check: "Are all mandatory documents for the new employee signed?" - Automated checklist, missing signatures escalated as workflow tasks.

Audit preparation: "Show all documents without a signature in Q3 2025." - Structured export list for the auditor.

┌─────────────┐     ┌──────────────────┐     ┌──────────────────┐
│  Document   │     │  Signature       │     │  Comparison      │
│  with       │────▶│  Detection       │────▶│  against         │
│  signature  │     │  (position,      │     │  reference       │
│             │     │   confidence)    │     │  signature       │
└─────────────┘     └──────────────────┘     └──────────────────┘
│
┌───────────┼───────────┐
▼           ▼           ▼
┌────────────┐ ┌────────┐ ┌────────────┐
│  High      │ │ Medium │ │  Low       │
│  match     │ │ match  │ │  match     │
└────────────┘ └────────┘ └────────────┘
│              │           │
▼              ▼           ▼
Automatically  Escalation   Blocked
accepted,      to human     Human
documented     with side-   review
by-side      mandatory
comparison
view

Important: Signature comparison is an anomaly detector, not a forgery detector. Signatures vary naturally - depending on the day, pen, and surface. The system identifies anomalies and escalates them to a human. It never claims "this signature is forged" or "this signature is authentic." That would be irresponsible.

Integration

Document Intelligence is a capability of the existing Document Agent - not separate software. Integration uses the same standardized interfaces:

• SAP DMS, SAP ArchiveLink - contracts and receipts from SAP archives
• SharePoint, OneDrive - document management via Microsoft Graph
• Email inboxes (IMAP/Exchange) - process attachments automatically
• File system watchers - monitor local directories
• REST API - for client-specific DMS systems

Document Intelligence capabilities are configured per tenant: which PII categories are detected, which redaction rules apply, which reference signatures are stored. All versioned, all in the Decision Layer.