Legal Operations
AI Legal Operations Assistant
Handles routine legal-ops coordination and matter tracking.
Legal Operations
AI Legal Document Classification
Incoming legal documents are read, categorized by type and tagged, so each one lands in the right file automatically.
Incoming documents pile up in shared inboxes and folders until someone has time to open, name and file each one. AI Legal Document Classification does that sorting for you. It reads each document, works out its type, tags it by matter and date and files it in the right folder. Anything it is unsure about goes to a person, so nothing is filed on a guess.
- Document type, matter and date tagged on arrival
- Each document filed to the right folder automatically
- Uncertain documents routed to a person for review
$4,400
20–30 working days
Optional maintenance $249/mo
What it is
AI Legal Document Classification reads each incoming document, works out its type, such as an NDA, MSA or lease, and tags and files it in your document management system before anyone opens it manually. Documents it is unsure about go to a person for review instead of being filed.
Why businesses buy it
Manual filing is slow, inconsistent and easy to fall behind on. A misfiled lease or NDA wastes time later, when someone needs it urgently and cannot find it. This build classifies and files every incoming document the same way, using your own document types and folder rules, and leaves the doubtful ones for a person. It is tested on your real documents before launch, with an accuracy report. The Scope Card fixes the document types, fields and systems in writing, so you know exactly what it sorts.
Problems this solves
Paralegals spend hours sorting and filing incoming documents
The build reads each incoming document and works out its type, such as an NDA, MSA or lease. It tags and files it in your document management system before anyone opens it.
Files end up in the wrong folder and are hard to find later
Classification follows the same rules every time, for up to three document types. Consistent tags make documents easier to locate in your system. Search and audits get simpler.
A misfiled document can be worse than an unfiled one
Documents the build is unsure about go to a person for review instead of being filed. That keeps doubtful cases out of the wrong folder.
Documents arrive through many routes and some are never filed
Incoming documents come through one agreed intake route, such as an inbox or upload folder. From there they pass to your document system as part of one flow.
A good fit if
Documents arrive in a shared inbox or upload folder in a mix of types, and someone currently opens each one to work out what it is before filing it.
You can name up to three document types, such as NDA, MSA or lease, and give us at least 20 real samples of each.
You want documents tagged and routed to the right folder or matter automatically, with anything unrecognized held for a person to check.
You want a human review queue for low-confidence classifications, not documents filed as a guess.
Not the right fit if
You need clause text, such as indemnification or termination terms, pulled out of contracts already sorted by type. See AI Clause Extraction.
You need renewal and notice dates tracked across a portfolio over time, not documents sorted as they arrive. See AI Contract Renewal Monitor.
You want broader internal coordination beyond filing, such as vendor questions or billing checks. See AI Legal Operations Assistant.
Your intake covers more than three document types. Add a note at checkout and we quote it, or start from our Custom AI enquiry form.
How it works
- Documents arrive through the intake route you choose, an email inbox or an upload folder, in whatever mix your firm normally receives, from a signed NDA to a scanned lease.
- Document Classification reads each one and works out its type against the up to three categories you defined, such as NDA, MSA or lease.
- Each document is tagged with its type, and any additional fields you set, such as matter or client, and validation rules check the classification makes sense.
- Anything the classifier isn't confident about goes into a review queue for the person you named, instead of being filed as a guess.
- Confirmed documents are filed into the destination system you connected, such as your document management or matter management platform, in the folder structure you already use.
- We test the build against 100 of your real sample documents before launch and hand you an accuracy report broken down by document type.
What you provide within 72 hours
Your portal lists these the moment you order. Delivery starts the working day after everything is in and your access is checked.
- Your business information (company basics, hours and brand voice), shared during intake, or confirmation we can reuse what you gave us on an earlier order.
- At least 20 real sample documents for each document type Classification should recognize, redacted if you need to.
- The exact list of document types and any extra fields, such as matter or client, to tag each one with.
- Access to the destination system classified documents should be filed into.
- The name of the person who reviews anything the classifier is not confident about.
- Admin access and API keys for every connected system, shared by adding our team as a user or creating a key you control, never by email.
- One decision-maker who can approve the document type list and sign off at launch.
- An API key for your own AI model account (for example OpenAI or Google Gemini), created for this build with a spending limit.
The 72-hour rule. Send everything on your checklist, including access, within 72 hours of ordering so your build starts on time.
Timeline
Start
Intake verified, sample documents and document type list confirmed.
Weeks 1–2
Classification rules and tagging logic built for your document types.
Week 3
Source and destination systems connected and the review queue configured.
Weeks 3–4
100 sample documents processed, accuracy report shared with you.
Week 4
Your review and two rounds of changes.
Go-live
Live, recorded handoff session, support starts.
| Option | Delivery time | Price |
|---|---|---|
| Standard | 20–30 working days | $4,400 |
| Express | 15–25 working days | $5,150 |
| Rush | 10–20 working days | $5,950 |
What you receive at handover
- AI Legal Document Classification, configured and deployed to your environment
- Classification and tagging rules for up to three document types, with a human review queue
- One intake route and connections to up to two systems, such as your document management system
- A test report with an accuracy report from 100 sample documents
- An admin guide, the recorded handoff session and 30 days of post-launch support
Expected benefits and how to measure them
- Can free paralegal time now spent filing by hand
- Helps documents land in the right place with consistent tags
- Makes incoming documents easier to find soon after they arrive
- Filing time per document
- Time a sample of manual filing before launch. Compare with review-queue time per document after.
- Documents sent for review
- Count review-queue items each month as a share of documents processed.
- Misfiled documents found
- Spot-check a sample of filed documents each month, before and after launch.
Before you start: Record weekly document volume, average filing time and the results of a spot-check for misfiling.
These are things to track, not promised results. Outcomes depend on your data, your team and your market.
Running costs
The build price is one-time. Running AI Legal Document Classification afterwards costs roughly $30–200/month depending on page volume, covering OCR and AI usage plus storage, billed directly in your own accounts.
AI usage during the build and testing is also billed to your accounts, so you keep ownership of every provider relationship. Nothing runs through us.
Ask about running costsCustom requirements
If you need something outside the Scope Card, add a note at checkout. You get a written Change Quote, and that work only starts once you accept it. Your original order runs on its normal timeline either way. Larger or bespoke projects go through the Custom AI request form instead.
Request a custom versionKeep it running
We recommend monthly maintenance: monitoring, fixes, and monthly change hours, which cover a new document type, an updated tag or a changed filing rule. Maintenance starts after the 30 days of support, bills monthly, and can be cancelled any month.
$249/mo (the minimum fee, includes 2 change hours)
Optional. Starts after the post-launch support period. Cancel any month.
How maintenance worksHow this compares
| Do it yourself with a SaaS tool | Hire a custom agency | Upmark Labs | |
|---|---|---|---|
| Price | A document-filing add-on bills per user or per document processed every month | A records consultant charges for a one-off filing overhaul | Ours is one fixed price, shown on this page before you buy |
| Scope | A document-filing add-on is a generic classifier you have to train yourself | Scope is agreed during the project | Ours is written on the Scope Card before purchase |
| Filing rules | A document-filing add-on ships default categories that rarely match your folder structure | Filing rules depend on what was scoped | Ours files into the folder structure you already use |
| Delivery | Sign-up is instant, training it on your documents is not | Typically several weeks before work even begins | Ours has a fixed delivery time shown before you buy, with faster options |
Questions about this product
How much does AI Legal Document Classification cost?
The build is a one-time fixed price, shown in the price panel on this page next to each delivery speed, and it is confirmed with your Scope Card. It covers the classification rules, tagging and filing logic, the human review queue, connections to your source and document system, and the accuracy report run before launch. There is no charge from us per document afterwards.
How is AI Legal Document Classification different from AI Clause Extraction?
Classification is the sorting step: it works out what a document is, tags it and files it, before anyone reads it closely. Clause Extraction goes further into already-identified contracts and pulls specific clause text and values, such as indemnification or termination terms, into structured fields. If you need both, running Classification first gives Extraction a cleaner set of contracts to work from.
Does AI Legal Document Classification decide how a document should be handled legally?
No. It works out the document type and files it in the right place, it does not interpret the content or advise on how to act. Anything it isn't confident about goes to the reviewer you named, and any legal judgment about a filed document always stays with a qualified person on your team.
How much does AI Legal Document Classification cost to run each month?
Roughly $30 to $200 a month in your own accounts, covering OCR and AI usage plus storage. The figure scales with how many document pages pass through it, so clearing an old backlog costs more than sorting new arrivals each month. We charge nothing per document, and monthly maintenance is optional if you want new tags or rules added.
How long does AI Legal Document Classification take to launch?
The delivery time is fixed before you buy and shown in the delivery panel on this page, with faster speeds where offered. It starts once your document types, folder rules, sample documents and system access are in. Most of the build goes into tuning classification against your real documents and writing the accuracy report, so you see how it performs before launch.
What access does AI Legal Document Classification need to our systems?
It needs admin access and API keys for the source and destination systems you connect, such as your inbox and your document management system, shared by adding our team as a user or creating a key you control, never by email. It also needs at least 20 real sample documents per document type to train classification on properly.
Can I add a fourth document type to AI Legal Document Classification later?
Small changes, such as a new tag or an adjusted filing rule within your existing three document types, fit inside the monthly change hours that come with maintenance. A fourth document type is a bigger change and gets a written Change Quote first.
Stop opening every document just to see what it is.
Order AI Legal Document Classification and incoming documents are sorted, tagged and filed on a fixed delivery date. The scope above is what you get, in writing, before you pay.
Works well with
Legal Operations
AI Legal Knowledge Base
Organizes precedents, templates and guidance into a searchable base.
Legal Operations
AI Legal Intake
For in-house legal teams: captures and triages incoming legal requests from the business.