Personal information, found.
Find personal information on every page, including special category data, with a confidence score and a source span for every finding.
The problem.
Personal information is more than names and dates of birth. A sentence about someone's health, an opinion in a manager's email, a salary figure in a table. Keyword search finds what you already thought to look for and misses the rest.
What Redactics does.
Redactics uses layered detection. Pattern matching and Azure AI Language handle the deterministic volume: identifiers, contact details, dates, references and account numbers. Contextual language models handle what needs reading: health, opinions, relationships and other special category data. Every finding is categorised, scored, linked to the exact span in its source and redacted automatically, ready for review.
- Categories aligned to UK GDPR, including special category and criminal offence data
- Confidence score on every finding
- Deterministic rules where rules work; language models where context is required
- Custom categories and organisation-specific identifiers
Findings by category
How findings were made
- For your teamStart from the redacted result
- Reviewers begin with redactions grouped by person and category, ordered by confidence, rather than with a blank page and a search bar.
- For your recordsSpecial category data caught early
- Health, ethnicity, sexual orientation and similar information is identified and redacted during processing, not discovered after export.
- For your security reviewModels run in your region and never train on your data
- Language model calls stay within Azure OpenAI in your chosen region. Prompts and outputs are not used to train any model.
Redact your first document set.
Try Redactics on a synthetic sample set, or talk to us about your documents.