Datics AI
AI for Legal tech

Recordly by Datics AI

Ask a question of a matter's files and get an answer that cites the page, or says the files are silent.

Case teams stop paging through exhibits for one date. Recordly answers from the matter's own files, cites the page behind each claim, and declines when the files do not cover the question.

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

Merrow & Vance · Recordly

Demo

When did Thistle first learn of the brake defect?

Answer with 2 citations

  • From this matter's files only, scoped before ranking
  • Each claim cited to its page
  • Declined where the files are silent

Scoped to the matterEvery claim citedDeclines, never guesses

Try it step by step

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

Try it step by step

Recordly on a fictional customer.

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

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

Merrow & Vance · Recordly

Demo

  • When did Thistle first learn of the brake defect?

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

Cited answer · Okafor v. Thistle Logistics

Merrow & Vance · matter files

Recordly
Earliest notice
Fleet manager email, March 14, 2025 · Exhibit 12, p. 2
Done
Corroboration
Maintenance log, April 2 · Exhibit 7, p. 9
Done
Recall
Not in the matter files · declined
Check
Scope
This matter only, within the user's access
Done
Originals
Opened from the document system by signed link
Done

Every claim cites its page. Information for the case team, not legal advice.

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

What it does

What Recordly can do.

Cited answers over case files, transcripts and archives, scoped to the user's tenant, matter and clearance before anything is ranked, with every claim linked to its passage and originals left in your document system.

Scope before ranking

Retrieval filtered by tenant, matter and clearance before ranking, and closed when a lookup fails.

Cite, or decline

Each claim cited to its passage; when the files are silent, the answer says so.

Originals stay in your system

Your document system sends approved text and metadata; files are opened from it by short-lived signed links.

OCR chosen on your documents

Self-hosted OCR chosen by side by side tests on your documents, with a fast path for digital PDFs.

Self-hosted when you need it

Models on your own GPU host, so no record goes to an outside AI service.

How it works

Your document system pushes approved text, metadata and a source ID, and keeps the file. Retrieval is filtered by tenant, matter and clearance before ranking; the model answers only from the passages it was given and cites each one, or declines.

Built on self-hosted cited answer and archive search engines we have delivered for live document products.

NenoBrief by Neno Technologies

Document AI · Cited answers in production

Archive officers get cited answers inside their live document system, files never copied

Archive records could not reach an outside AI. Now the client's live document system calls our self-hosted gateway for cited answers.

Brownfield AIInside a live productCited answers
Read case study

NenoDoc Lexicon by Neno Technologies

Document AI · Self-hosted workspace

Archive teams get cited answers in French and English on one client-owned GPU

Sensitive archives could not go to an outside AI. Now teams ask in French or English and get answers cited to the page, all on the client's GPU.

AI-native productCited answersDocument intelligence
Read case study

WikiTeq

AI engine · Cited document answers

WikiTeq's self hosted AI chat now answers from its documents, citing every source

The chat could not answer from the firm's own documents. Now a separate retrieval service feeds it passages and shows the source of each answer.

Brownfield AICited answersInside a live product
Read case study

Why it sells

What Recordly does for your business.

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

Answers attorneys can use

Every claim has its page, so they check instead of doubt.

No new place for files

Originals stay in your system, which your customers' counsel asks about first.

A paid tier

Cited answers sold as part of a higher plan.

Built for:Legal document and knowledge software

Controls

What Recordly 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

    Attorneys, paralegals, records and knowledge teams

  • What it connects to

    Your document system through its APIs: approved text, metadata and source IDs

  • What a person approves

    Answers inform; people decide what goes into the case

  • 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 Recordly.

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

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

    Case teams get cited answers from their own matter files

    • Scope before ranking
    • Cite, or decline
    • Originals stay in your system
    • 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 getRecordly 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 Recordly 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 Recordly 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 Recordly:

    • OCR chosen on your documents
    • Self-hosted when you need it

    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 Recordly.

Can one firm's users see another matter's documents?

No. Retrieval is filtered by tenant, matter and clearance before ranking, and unknown users or failed lookups get nothing.

Does it copy our customers' files?

No. Your system sends approved text and metadata; the file stays where it is and opens from there by a signed link.

Does it give legal advice?

No. It says what the files say and cites them. The attorney decides what it means for the case.

See Recordly on your own product.

Bring your product and one workflow. In 30 minutes we look at where Recordly 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 Recordly in your platform