Skip to content
Private Preview
Join Waitlist →

Redact Sensitive Information
Before AI Sees It.

Names, account numbers, identifiers — masked during browser-local detection and redaction for measured born-digital formats: text-layer PDFs, Word files, spreadsheets, CSV, and plain text. Miss something? Redact it yourself.

IN-BROWSER REDACTIONLOCAL ORIGINAL VALUESWORKS OFFLINE
Redactorr App ShellBrowser local
Canvas
Upload measured formats
Engine loadingLocal path

Redact before AI sees the original.

Start with measured born-digital files, review locally, then work from the redacted version.

Canvas
LocalMeasured formatsAU pack
Drop a document
PDF, DOCX, XLSX, CSV, and TXT.
Choose file
In private preview with compliance teams across
Healthcare
Legal
Finance
Government
Insurance
Enterprise
TRUST CENTER

Original Values Stay Local During Redaction

Watch Redactorr detect and redact sensitive information inside your browser. Reviewed redacted output can then move to Vault, sharing, or AI workflows when you choose.

patient-intake-form.pdf0/23 REDACTED
Patient Details
Patient Name: Margaret Elizabeth ThompsonFull Name[Full Name]
Date of Birth: 14/03/1987Date of Birth[Date of Birth]
Medicare No: 2951 48376 2Medicare Number[Medicare Number]
TFN: 648 293 517Tax File Number[Tax File Number]
Address: 17 Banksia Crescent, Hawthorn VIC 3122Home Address[Home Address]
Phone: 0412 839 274Phone Number[Phone Number]
Email: [email protected]Email Address[Email Address]
Emergency Contact
Name: James Robert ThompsonFull Name[Full Name] (Spouse)
Phone: 0438 192 653Phone Number[Phone Number]
Insurance & Financial
Insurer: Medibank Private #MPH-4829163Insurance ID[Insurance ID]
Employer: BHP Group LtdOrganisation[Organisation]
Bank (claims): BSB 063-241 Acc 1094 7823Bank Account[Bank Account]
Clinical Notes — Dr. Anand PatelFull Name[Full Name], 12 March 2026Date[Date]
Diagnosis: Type 2 Diabetes MellitusMedical Condition[Medical Condition]
Medication: Metformin 500mg BDMedication[Medication]
Result: HbA1c 7.8%Medical Result[Medical Result] (suboptimal control)
Also treating: chronic lower back painMedical Condition[Medical Condition] at Royal Melbourne HospitalOrganisation[Organisation]
Referred to: Dr. Sarah ChenFull Name[Full Name] (Endocrinology)
Next appt: 28/03/2026Date[Date] at Hawthorn Medical CentreOrganisation[Organisation]
Licence (ID): VIC 0839274192Driver's Licence[Driver's Licence]
REDACTORR ENGINE0
Full NameMargaret E. Thompson
Date of Birth14/03/1987
Medicare Number2951 48376 2
Tax File Number648 293 517
Home Address17 Banksia Cres, Hawthorn
Phone Number0412 839 274
Email Address[email protected]
Full NameJames R. Thompson
Phone Number0438 192 653
Insurance IDMPH-4829163
OrganisationBHP Group Ltd
Bank AccountBSB 063-241 / 1094 7823
Full NameDr. Anand Patel
Date12 March 2026
Medical ConditionType 2 Diabetes
MedicationMetformin 500mg BD
Medical ResultHbA1c 7.8%
Medical ConditionChronic lower back pain
OrganisationRoyal Melbourne Hospital
Full NameDr. Sarah Chen
Date28/03/2026
OrganisationHawthorn Medical Centre
Driver's LicenceVIC 0839274192
Entities Found0
Categories0
StatusREADY
SCAN
DETECT
REDACT
CLEAN
Browser-local detection
Browser-local redaction
We never see your data
AEGIS Detection Pipeline

15 layers. Nothing escapes.

Two pre-detection layers prepare the document. Twelve specialist engines run simultaneously. One final gate releases nothing it hasn't verified.

INGEST
Pre-detection
Two layers prepare the document before any specialist engine fires.
01RECON

Document understood before it is judged. Nothing placed without context.

02SENTINEL

The right specialist is always on the document. No entity handled by the wrong engine.

COMMANDER
COMMANDER
orchestrates 12 specialist engines
Each engine handles a distinct detection domain. They run in parallel, then converge.
L03
Identifier
Names, phones, direct IDs
Identity
L04
Medical
Medicare, AHPRA, diagnoses
Medical
L05
Tax
TFNs and financial IDs
Financial
L06
Address
Street, postcode, location
Location
L07
Contact
Email, phone, comms handles
Contact
L08
Form
Fields, tables, structure
Reference
L09
Entity
People, orgs, linked records
Identity
L10
Window
Nearby context windows
Reference
L11
Context
Narrative clues and aliases
Reference
L12
Fusion
Combine overlapping signals
Reference
L13
Score
Confidence and risk rank
Reference
L14
Arbitrate
Resolve conflicts before gate
System
FINAL GATE
15 WARDEN

The final gate. Nothing unverified is released.

Medical Referral
Specialist Referral Letter
14 / 14 REDACTED

Document type: [DOC_TYPE]

Referring Practitioner: [NAME] — AHPRA: [AHPRA]

Patient DOB: [DOB], Medicare: [MEDICARE], TFN: [TFN]

Address: [ADDRESS] | Phone: [PHONE] | Email: [EMAIL]

Referral to: [ORG]

Physician: [NAME]

Diagnosis: [DIAGNOSIS]

Billing: BSB/Account: [BSB/ACC] | Access token in notes: [TOKEN]

Platform workflow

Redaction is the first step.

After sensitive values are replaced, Redactorr helps teams keep working with the processed version: save the redacted session, ask AI about the reviewed document, or share a controlled package.

01

Detect and redact locally

Detection and redaction run in your browser, so original sensitive values stay local during the redaction step.

02

Save the processed session

Vault is for redacted or tokenized sessions, review history, and processed outputs.

03

Ask AI about the redacted document

After review and consent, the assistant works from redacted document context instead of raw values.

04

Reuse the structure safely

Turn a production-shaped document into synthetic examples for onboarding, process documentation, and agent testing.

Start with a redacted document
Behind the Engine

Redact Locally. Keep Working.
One Relentless Mission.

It started with a simple question: why does every AI tool demand your raw data? That question became an obsession. 3,000+ detection patterns. 36 industry engines. Every edge case hunted down.

Read Our Story

The architecture is the privacy boundary.

Tokenized, Not Blacked Out

Traditional redaction destroys context. Redactorr replaces sensitive data with meaningful tokens that preserve document structure.

Traditional
Dear ████, your salary of ████ has been approved.
Redactorr
Dear [PERSON_NAME_1], your salary of [SALARY_1] has been approved.

Browser-Local Redaction

Detection and redaction run in your browser. Original sensitive values stay local during detection and redaction for measured born-digital formats, including text-layer PDFs, Word files, spreadsheets, CSV, and text-like files. Scanned pages, photos, and handwritten forms are active product directions with separate gates.

Your DocumentBrowser
Redacted OutputBrowser
Server UploadsNONEServer

100+ Entity Types

Names, addresses, Tax File Numbers, ABNs, Medicare numbers, credit card numbers, phone numbers, and hundreds more across 36 domains. Built for Australian documents.

Full NameEmail AddressPhone NumberAddressTax File NumberABNCredit CardMedicare NumberPassportBSBDate of BirthIP Address

Your Rules, Not Ours

Manual redaction for surgical precision. Custom patterns for your business-specific identifiers. The engine proposes. You decide what gets redacted.

Select any text and redact manually
Build custom patterns for proprietary codes
Accept, dismiss, or reclassify detections
Retag entities to the correct type
DOMAIN PACKS

36 Industries. One Dedicated Engine Each.

Enable an industry pack for industry-specific detection. Add custom patterns for your organisation's own identifiers. Manually redact anything else. Your data. Your rules.

Healthcare & Medical Pack

Patient records contain the most sensitive data any organisation handles. There is no margin for error.

WHAT REDACTORR DETECTS
Patient names
Medicare numbers
IHI (Individual Healthcare Identifier)
Practitioner registration
Diagnosis codes (ICD-10)
Medication details
Provider numbers
REAL-WORLD WORKFLOW
A clinical researcher needs AI to summarise 500 patient discharge notes. Redactorr masks every patient identifier, Medicare number, and diagnosis — the AI analyses treatment patterns, not people.
15 specialised patterns|10 entity types
Explore Pack

Finance & Banking Pack

Account numbers, BSBs, and transaction records are the highest-value targets for data breaches.

WHAT REDACTORR DETECTS
BSB numbers
Account numbers
Credit card numbers (PAN)
ABN/ACN
Transaction references
SWIFT/BIC codes
Superannuation member IDs
REAL-WORLD WORKFLOW
A financial analyst needs AI to identify trends across 12 months of transaction data. Redactorr strips account numbers, BSBs, and customer names — the AI sees patterns, not identities.
14 specialised patterns|9 entity types
Explore Pack

Education Pack

Student records, ATAR scores, and enrolment data are protected under privacy legislation. Schools can’t afford leaks.

WHAT REDACTORR DETECTS
Student IDs
ATAR scores
USI (Unique Student Identifier)
Enrolment numbers
Parent/guardian names
Teacher registration numbers
Academic transcripts
REAL-WORLD WORKFLOW
A university administrator needs AI to analyse enrolment trends across 5 years of records. Redactorr removes student names, IDs, and ATAR scores — the AI works with demographics, not individuals.
8 specialised patterns|7 entity types
Explore Pack
1 / 27Legal & Law Firms Pack

Process Any Document.

Every format runs through all 15 AEGIS layers. Full pipeline. Every time.

PDF
PDF Documents
Text-layer PDF support
Scanned PDF OCR preview path
Vulnerability scanning before processing
DOCX
Word Documents
Track changes preserved
Headers, footers, and footnotes
Embedded objects and metadata
XLSX
Spreadsheets
Multi-sheet workbook traversal
Formula-resolved cell values
Named ranges and table structures
IMG
OCR Roadmap
Printed scans and photos under gate
Export leakage proof required
Handwriting requires HTR decision
ALSO SUPPORTSCSV, RTF, HTML, JSON, XML, PNG, JPEG, TIFF, ODT, PPTX, TXT + more
15+
document formats
100+
entity types detected
15
AEGIS layers per file
0
server uploads
Security

Trust isn't a paid feature.

Same infrastructure on every plan.

Full security details →
Local
original values during redaction
100%
client-side processing
Offline
Kill your WiFi. It still works.
Authentication & Access

Workspace access is gated by authenticated accounts, role-aware permissions, and session controls.

Data Protection

Detection and redaction run in your browser. Original sensitive values stay local during detection and redaction. Processed redaction sessions can be saved to Vault when you choose.

Detection Coverage

Australian document patterns, financial identifiers, health references, and industry-specific entity types are mapped for review before export.

Review History

Review history focuses on processed redaction sessions, accepted detections, exports, and share-ready redacted packages.

Secure Sharing

Passphrase-protected links, automatic expiry, view-count limits, instant revocation. Selective unredaction per recipient.

Detection Integrity

3,000+ detection patterns. Mathematical verification for every structured identifier. PDF vulnerability scanning before processing begins.

Australian-First

Built for the way Australia works

Global tools treat Australian identifiers as edge cases. We treat them as the default. Every AU government ID, healthcare number, and financial identifier ships built-in — not as an add-on.

38
AU government identifiers
TFN, ABN, ACN, ARBN, Medicare, BSB, DVA, WWCC, Director ID, ImmiCard, Visa Grant, Centrelink CRN, IHI, HPI-I, HPI-O, NDIS, PBS, USI, and more — structured AU IDs in a single engine.
8
Mathematical verification algorithms
TFN mod-11, ABN mod-89 weighted check, ACN mod-10, Medicare mod-10, Centrelink CRN mod-26, Individual Healthcare Identifier checksum, BSB bank-prefix directory, AU postcode range. Candidate numbers that fail the algorithm are dropped — no false captures.
36
Australian laws and regulations mapped
Privacy Act 1988, Healthcare Identifiers Act 2010, My Health Records Act 2012, NDIS Act 2013, Migration Act 1958, Social Security Act 1991, Superannuation Industry (Supervision) Act 1993, and 29 more — each entity type linked to its governing legislation.
36
Australian banks in BSB directory
Big 4 plus Macquarie, Bendigo, ING, Suncorp, BOQ, St.George, Bankwest, and 25 more. BSB validation runs against the full AusPayNet institution registry — no server call needed.
Privacy Act 1988
+ data-boundary review
Detection and redaction run in your browser. Original sensitive values stay local during detection and redaction, while processed outputs can move into the next workflow when you choose.
36
Australian industry domain configurations
Construction, healthcare, legal, insurance, immigration, aged care, government, real estate, and 28 more. Each configuration is tuned for Australian document patterns and the identifiers that matter in that industry.

Free Forever. Pro When You Need It.

The full detection engine is free, including manual redaction. No trials that expire. Upgrade for unlimited scans, document upload, and custom patterns.

Free

Freeforever

No credit card required. No expiry.

5 documents/month
Launch-safe formats — PDF, Word, Excel, CSV, and text
10-page max per document
1 AI session/month
Mandatory watermark
Runs in your browser
Community support
Most Popular

Pro

A$99/month

A$82.50/mo billed annually (2 months free)

For professionals who handle sensitive data daily.

Everything in Free, plus:
Unlimited documents, all formats
Full 15-layer AEGIS engine — complete coverage
150 AI sessions/month
50 custom patterns
Audit trail
Priority support

Team

A$199/month

3 seats included. Additional seats A$69/seat/mo.

Drag to adjust team size
3 seats
3
5
10
20
50
Everything in Pro, plus:
150 AI sessions/seat/month
Shared team workflow
Shared pattern library
Dedicated support
Up to 50 seats
Enterprise

Built for teams above 50 seats.

Custom pricing. Bespoke engine configuration. Dedicated support. Custom integrations and deployment planning.

100% Processed in your browser.