Datics AI
AI for Legal tech

Redactly by Datics AI

Names, contact details, account numbers and marked terms found and proposed for redaction, with a reason for each.

Staff stop reading every page with a black marker. Redactly proposes each redaction with its reason, a person approves or rejects every one, and the original file stays exactly as it was.

See it in your platform Try the demo

Built into your codebase and shipped under your name, on an engine we license to you.

tessaline.example/merrow-vance/matters/okafor-v-thistle/production-3

Merrow & Vance · Redactly

Demo

Prepare the Thistle maintenance logs for production.

23 redactions proposed, none applied

  • Each with its reason and page
  • 2 privilege list terms left for the attorney to decide
  • Produced only after a person approves each one

5 files readReasons on every proposalA person approves

Try it step by step

Illustrative demo on a fictional agency and firm. Not client work.

Try it step by step

Redactly on a fictional customer.

Merrow & Vance (fictional). Step through the conversation, then see what Redactly hands back, the way your Build Sprint would build it on synthetic data.

tessaline.example/merrow-vance/matters/okafor-v-thistle/production-3

Merrow & Vance · Redactly

Demo

  • Prepare the Thistle maintenance logs for production.

Step 1 of 5

Illustrative demo on a fictional agency and firm. Not client work.

What it hands back

tessaline.example/merrow-vance/matters/okafor-v-thistle/production-3

Redaction set · Maintenance logs

Merrow & Vance · Okafor v. Thistle Logistics, production 3

Redactly
Non-party names
11 proposed · parties left visible, per the matter's rules
Waiting
Phone numbers
7 proposed · Bates page shown for each
Waiting
Account numbers
3 proposed · Bates page shown for each
Waiting
Privilege list terms
2 matches · privilege is the attorney's call
Check
Originals
Kept unchanged · redacted copies made on approval
Done

Redactly proposes. A person approves every redaction, and the attorney decides privilege.

Illustrative demo on a fictional agency and firm. Not client work.

What it does

What Redactly can do.

Redaction proposals before a file is released or produced: names, contact details, account numbers and terms your customer marks as privileged, each with its reason and page, approved one by one by a person, with the original kept unchanged.

Identifiers found

Names, phone numbers, emails, addresses and account numbers found on every page, with the page shown.

Marked terms matched

Terms on your team's privilege list matched and proposed, never judged.

A reason for every proposal

Each proposed redaction says why it was proposed, so a reviewer can decide quickly.

Approved one by one

Nothing is redacted until a person approves it, and nothing is released until every proposal is decided.

Originals kept

Redacted copies are made on approval; the original stays unchanged in your system.

How it works

Identifiers are found on each page and masked before any text reaches a model, and your customer's marked terms are matched from their own list. Each proposal carries its reason and page; approved redactions are applied to a copy, and the original is kept.

Built on identifier masking we have delivered, where names never reach the model, and on locking for terms an organization has approved. Proposing redactions with reasons for a person to approve is what the Build Sprint adds.

MIRA

Privacy · Identifiers kept from the model

Clinics sign up, pay per provider and run their own AI patient intake

The AI intake worked in three practices but was hard coded. Now any clinic signs up, pays per provider and runs it, and names never reach the model.

AI-native productMulti-tenantHIPAA-aligned
Read case study

NenoDoc Lexicon by Neno Technologies

Document AI · Writing that keeps the facts

Archive indexers fix grammar and style without a name, date or figure changing

AI rewrites can quietly alter names and numbers. Ours edits only flagged spans, and approved terms are locked before the model sees them.

AI-native productHuman approvalDocument intelligence
Read case study

Transcripts U.S.

Court reporting · Encrypted release

Attorneys receive deposition transcripts that even the marketplace cannot read

The marketplace could once read every transcript it held; now each file is encrypted in the agency's browser and opens only in the paying attorney's.

Brownfield AIInside a live productPermission-aware
Read case study

Why it sells

What Redactly does for your business.

What your customers get, and what it does for your renewals and pricing.

Fewer missed identifiers

Every page is checked, and every proposal is shown to a person.

Faster productions

Reviewers decide proposals instead of reading every line.

A clear line on privilege

It matches marked terms and leaves the decision to the attorney.

Built for:Legal document and knowledge software

Controls

What Redactly touches, and who approves.

Your customers' data is not used to train models for anyone else and stays in your cloud. Built and tested on synthetic or test data.

  • Who uses it

    Paralegals, litigation support teams, records and release staff

  • What it connects to

    Your document store, production sets and your team's privilege list

  • What a person approves

    A person approves every redaction; the attorney decides privilege

  • Switch per customer

    On or off for each customer, with data settings their admins control.

See all controls and how we handle confidential legal records

How to get it

Two steps to a finished Redactly.

Start with a three-week Build Sprint. Add more only if you want it.

  1. First · Build Sprint · $10,000 fixed

    Files released with every redaction approved by a person

    • Identifiers found
    • A reason for every proposal
    • Approved one by one
    • In your staging, behind a feature flag
    • Delivered as pull requests
    • A test set your team reviews
    1. Week 1Setup
    2. Weeks 2 to 3Build
    3. You getRedactly in your staging and a fixed production quote
    Your time
    About 2 to 3 hours a week from a product owner
    Data
    Synthetic or test data, never your customers' customers
    The fee
    Counts toward production
    See Redactly in your platform See a sample Build Sprint Pack

  2. Then · Live in production

    A finished product, yours to run

    • Fixed quote
    • Tested before launch
    • Switch per customer
    • A finished, working Redactly in your product
    • Runs in your cloud, under your name
    • Fixed quote, agreed before we start

  3. Optional · Add more later

    Only if you want it

    More of Redactly:

    • Marked terms matched
    • Originals kept

    Another module:

    • Each one quoted on its own
    • Nothing ongoing unless you ask

Already built or tried AI? Get it scored with the AI Scorecard. Need something else? Start with a Planning Sprint.

FAQ

Questions about Redactly.

Does it decide what is privileged?

No. It matches terms your customer has marked and proposes them with a reason. The attorney decides privilege.

Can it release a file on its own?

No. A person approves every redaction, and the file is released or produced only after that.

What happens to the original?

It stays unchanged. Redactions are applied to a copy once they are approved.

See Redactly on your own product.

Bring your product and one workflow. In 30 minutes we look at where Redactly fits, what it would cost to serve and what your customers' security review will ask.

Book a 30-minute Product Review All legal tech modules

Calls run in US Central time. No generic AI presentation: we discuss your product, users and production constraints.

See Redactly in your platform