About Us
Edito: The Essential Tool for Document Management
Modular software to manage, protect, and automate PDFs: from Italian OCR to GDPR-compliant anonymization, through to workflows and license controls. Designed for law firms, public administration, and businesses in Italy.
Data in the EU
Privacy by design
No training on your data
Why Does Edito Exist?
Every day, professionals in law firms, public administration, and businesses waste time on manual copying, renaming, filing, exporting, and repetitive document checks. Transcription errors, typos, unredacted sensitive data, unverified metadata: traditional document management takes away valuable hours that could be dedicated to higher-value activities.
Edito was created to remove the burden from document workflows and make them secure, fast, and compliant.
Security
Control
Automation
Returns Time to Professionals
Automates manual and repetitive tasks, such as PDF transcription, searching for tax data (Tax ID/VAT), and redacting sensitive data word by word. Leaves people to do the work that requires experience and judgment.
Security and Compliance with Specialized AI
We use AI models trained on Italian datasets and managed on controlled systems. We do not rely on generic solutions that could expose chats, logs, and data to third parties.
What Is Edito
Edito is a modular document intelligence suite: activate only the modules you need today. Each module solves a specific problem, operates autonomously, and integrates with others for complex workflows.
EditoAI
Multilingual OCR optimized for Italian, with PDF to Word conversion. Automatic extraction of structured entities: from user-definable documents with a simple prompt (orders, attendance registers, customs documents, etc.), and custom fields via entity recognition. Support for scanned, photographed, or digitally native documents.
Edito Automatica
Programmable document workflows to eliminate repetitive operations. Automatic numbering and filing, label and barcode generation, conditional document routing, and integrations with existing systems (ERP, CRM, PEC, archiving). Reduces processing times and minimizes human errors.
Edito Omissis
GDPR-compliant selective and bulk anonymization and pseudonymization. Automatic detection of sensitive data (personal, health, judicial) with the option for human review pre-redaction. Complete report for each operation, activity log for audits, and export in PDF/A format for compliant archiving.
Edito Probo
Automatic verification of font licenses, embedded images, and metadata in PDFs. Identifies copyright-protected assets, detects sensitive metadata to remove, generates shareable reports for legal compliance and pre-publication verification.
Our Values
Privacy by design
Data remains the property of the client, processed and stored exclusively in the EU (GCP Europe). No extra-EU transfers, no training on client data without explicit consent. Complete logs and granular permissions always accessible for GDPR audits and compliance.
Italian for Italy
AI models trained on Italian datasets, NER rules optimized for local acronyms and formats (Tax ID, VAT, IBAN, PEC), UX designed for Italian administrative and legal practices. We do not adapt US or global solutions: we develop for the Italian and European market.
Simplicity
Clean interfaces, workflows with few steps, results verifiable in real time. No complex configurations or extensive training: Edito modules work immediately, with sensible default settings that can be customized when needed.
Transparency
Technical limitations and documentation always made explicit. Quality indicators (confidence score, OCR accuracy, entity extraction coverage) visible and downloadable. Complete reports on every operation to ensure audit trail and verifiability.
AI Responsibility
Curated datasets with verified licenses, respecting copyright and intellectual property. Human review (human-in-the-loop) on critical tasks. Complete traceability: log of every automated decision, versioned models, rollback and audit capabilities.
Proof That Matters
Concrete examples of our technology applied in R&D and production contexts.
Anonymization for NPL Securitization
Problem:
A consortium of 11 credit institutions needed to prepare a representative set of NPL (Non-Performing Loans) files for the due diligence of a €205 million securitization. All documents had to be anonymized in compliance with GDPR.
Result:
With Omissis®, 45,000 pages were anonymized, with a 90% saving compared to manual work and 65% higher efficiency compared to AI competitors. The material was delivered on time, confirming Omissis® leadership in document management for the regulated financial sector.
Data Breach Prevention: Lepida (POC)
Problem:
Medical documents (medical histories, reports, clinical records) shared among operators with risk of inadvertent exposure of privacy-protected sensitive data, causing potential data breaches and GDPR penalties.
Result:
POC with positive outcome for automatic identification and classification of sensitive entities (personal data, tax IDs, diagnoses, treatments) pre-sharing. The NLP technology developed is now the entity extraction and SmartOCR engine used in Omissis and Smart for compliant anonymization and large-scale data breach prevention.
Data Extraction from Complex PDFs: RadaeePDF SDK
Problem:
Extraction of structured data from non-standard PDFs (multi-page contracts, invoices with variable layouts, NPL documents for securitization) to populate databases. Standard commercial solutions failed on documents with complex formatting or partial corruption.
Result:
The People
We are a close-knit team with complementary expertise in document intelligence, AI/NLP, cloud architectures, and innovation management. We bring skills developed across Europe and Asia, in contexts ranging from Italian public administration to automotive and tech multinationals.
Our promise: to develop advanced document technologies that are powerful, compliant, and respectful. We do not compromise between technical performance and ethical responsibility.
Intimate Knowledge of the PDF Format
We design and develop SDKs for manipulating the ISO 32000 (PDF 1.7/2.0) and ISO 19005 (PDF/A) formats. We are co-authors of RadaeePDF SDK, used by approximately 8,000 developers in over 70 countries. We work at the internal document structure level to ensure fidelity, performance, and compliance even on complex or corrupted files. We have participated in PDF/Association and AIIM.
Ethical and GDPR-Native AI
We train, evaluate, and optimize NER networks, LLMs, and OCR specialized for the European context. Training on curated datasets with verified licenses, in full respect of copyright and intellectual property. Models trained on EU-hosted infrastructure, never on client data without explicit consent. We implement differential privacy, complete audit trails, and human-in-the-loop validation for sensitive tasks.
Architectures & Management
Certifications in Google Cloud (DevOps Engineer, Architect), IBM Cloud, Agile (ICAgile ICP-AHR), Innovation Management (ISO 56002), and Compliance (ISO 37301). Deployment on GCP Europe to ensure data residency, with Agile methodologies applied to R&D and operations.