Skip to content

Blog · Published · Updated

An AI knowledge base for a law firm: who can see what?

Short answer

An AI knowledge base in a law firm points to an approved template or research note and the source of the answer, but it uses only material cleared for shared use and the files the person asking may access. A title with a client's name can also reveal information, so the assistant does not show it. At Syntalith the app costs from €3,000 net. At 300 questions a month of 15 minutes each, it pays back in 1.4 months.

How we workDetails ↓

  1. 01Call30 minutes with an engineer, free
  2. 02PrototypeA working system on your process and data, free
  3. 03ImplementationTarget and fixed price in the contract; 50% at signing
  4. 04Acceptance50% once the agreed target is met
net per application, fixed price before contract
from €3,000
from signing the contract to acceptance
4–10 weeks
free prototype on your documents
€0

We belong to the OpenAI and Anthropic partner programmes and learn through their official courses. What this means ↓

Author: Syntalith · 3 min read

Example: the morning request inbox
Agent · ready

Statistics

Law firms and AI: statistics 2026

1.4 mo.

payback of a €3,000 app at 300 questions about templates and research notes a month: €2,618 of searching today, €399 with the app. Scenario.

Figures checked: 22 October 2026

Decide what the firm can share

Useful material may sit in files the person asking has no access to, and a similar topic gives no right to use it. Before you choose a search tool, settle which of the firm's work it wants to share more widely and who decides.

Three kinds of material
  • Shared library

    templates and research notes

    Cleared for shared use, with an owner who keeps them current.

  • Notes drawn from files

    after approval

    A version without client names or matter details, approved for wider use.

  • Client files

    matter team only

    They keep their restrictions, and the assistant does not show them to others.

Removing a name alone does not settle who may see the full content.

Handing a matter to another lawyer

The firm has approved an instruction for handing over matters: the person handing over names the folder with the current documents, describes the open tasks and gives a contact for questions. A lawyer asks the assistant what to prepare. A good answer points to the instruction and helps draft the note, while the lawyer adds the open tasks and the contact, because the instruction does not know them.

The archive may hold a similar note from another client's files. If the user has no access to them, the assistant shows no title, passage or quotation.

What a law firm knowledge base costs and when it pays back

Scenario: a law firm, 300 questions about templates and research notes a month
Today
300 questions × 15 min = 75 h (€2,618)
With the system, a person checks the output in 15% of the time
€393
Model, 1 call per case, Claude Sonnet 5.5
€5.97
Cost of one case
€8.73 today, €1.33 with the system
Saving
€2,219 a month

Payback of €3,000

1.4 months

The volume, the time and the checking share are the scenario's assumptions. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat. Model: 8,000 input tokens and 600 output tokens per call at Anthropic's rates, converted at the ECB rate of 1.1205 USD per euro on 22 October 2026.

When someone leaves a matter team

A permissions test before launch
  1. 01RemovalA test account loses access to a sample matter.
  2. 02Open chatThe same question in an open conversation returns no material.
  3. 03New sign-inAfter signing in again, the result is the same.
  4. 04HistoryThe firm decides whether earlier answers stay readable and exportable.
  5. 05TemplateAfter a template is withdrawn, the assistant does not present it as approved.

Removing access to a source does not delete copies someone has already downloaded outside the system. According to Eurostat (2025), 48.8% of EU enterprises that considered AI but did not use it named concerns about data protection and privacy, so this test is worth running before the first lawyer asks a question.

Check your existing document system first

Current system or a separate app
  • The problem is finding the right file

    a tidy library and permissions in the DMS

    no new app

  • The DMS has its own assistant

    assess the assistant in the current tool

    vendor licence

  • Knowledge spread across several systems

    an AI app that joins the sources with permissions

    from €3,000

iManage describes Ask iManage as an assistant that searches the repository, answers with citations and respects permissions, and the user guide describes asking questions across the repository. These are vendor statements to check on the firm's own account. When you are choosing between training, assembling documents and a knowledge base, compare the AI scopes for law firms. The first scope is one library of approved material, described on the private ChatGPT for law firms page.

Worked example · Scenario

How we count the payback: the firm's knowledge in one place

We run the same count for your firm in the free analysis.

€2,618

a month for finding answers to 300 questions in documents

Payback: 1.4 mo.

Our assumptions are 15 minutes to find the right template and check where it comes from, and checking in 15% of the old time. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat, for companies with 10 or more employees. Model cost: Claude Sonnet 5.5, about 6,000 + 500 tokens per answer from documents, at the ECB rate of 1.1205 USD per euro on 22 October 2026.

See the full calculation →

This is how we implement it in companies

All case studies →

Client results.

All projects →
foap.comcustomer service

foap.com customer service: 95% of replies are sent automatically.

Users from several countries write to foap.com, in several languages. The system reads the entire conversation and the terms of that person, and then sends a response in that person's language. Questions about money and exceptions go to the team with a ready draft, so they have to check and send them.

the system sends the answers itself, without human typing
95%
time from the arrival of the e-mail to the ready response (median)
30 s
e-mails that require a response receive a ready-made draft
100%
less work for every 1000 answers (estimate)
47 h

Data from foap.com production, October 20-21, 2026. Estimate: 3 minutes for handwritten response.

How foap.com customer service works →
Sample messages. Money matters always come to the person.

Other implementations

jaktako.design

studio projektowe

−87%

Time to look for new customers, every day

4 hours → 30 min

approx. 73 hours less per month (21 days of work)

according to the studio

How the agent loop works →
Signature Estates

real estate

approx. −90%

Operator time spent browsing portals, per day

2–3 hours → 20 min

approx. 45 hours less per month (21 days of work)

respect · contact the seller 5 minutes after the announcement

How the agent finds property listings →
Kuba Koziej, CEO and co-founder of MoreGrowth and board member at Natu.Care

Kuba Koziej

CEO and co-founder, MoreGrowth

„We started with my own AI agent. During the training that followed, I learned to build new applications myself. Today I am bringing this way of working with AI into my business. Working with Syntalith gave me exactly the skills and tools I needed.”

View the original training review on LinkedIn ↗

When an off-the-shelf tool does not fit, we build your own.Book a free process review (30 min) →

How we build automation and agents

From a conversation to a working system in four steps.

  1. 01 · 30 min

    Free process review

    €0

    You're talking to an engineer. You receive the written plan within 2 business days.

  2. 02 · 5 days

    Free prototype

    €0

    The system works on 20-100 cases that your team has already handled. You see every result.

  3. 03 · 2–16 weeks

    Build

    50%

    Fixed price and goal written in the contract. First installment upon signing.

  4. 04 · after reaching the goal

    Reception

    50%

    You pay the second installment when the system reaches its target on your cases.

How a free prototype is created

Mon.

We set a goal

What result do you consider good?

Tue–Wed

The system is working

It goes through your affairs, one by one.

Thu

We compare

We check every difference with the team's work.

Fri

Result and price

List of errors and fixed implementation price.

You choose the matters. We anonymize them upon request, they stay in the EU and we delete them after the test.

On the market, such a test usually costs from PLN 3,000 to PLN 8,000.

Book a free process review (30 min)

We establish a prototype during a free analysis.

Data checked on October 25, 2026.

„Is my data safe?”

Yes. You choose where they go: from your company account to the model on your server.

  1. 00Employee's private account

    Customer and company data ends up in an account that the company cannot see or control. There is no data processing agreement, so it is a violation of the GDPR. When an employee leaves, the chat history goes with them.

  2. 01ChatGPT or Claude corporate account

    The provider does not use your data to train models. A copy of the queries remains in his logs for up to 30 days.

  3. 02API with zero retention (ZDR)

    The provider processes the request and does not save anything. It requires his consent, we prepare the application together.

  4. 03Processing in the EU

    Queries are counted and stored in Europe: OpenAI in the EU region, Claude via clouds with the EU region.

  5. 04Model at your place

    The open model runs on your server or in your cloud in the EU. The data does not go outside the company.

What we do with every implementation

  • Confidentiality agreement and data processing agreement before we receive any data.
  • You choose the cases for the prototype and we anonymize them upon request.
  • The data stays in the EU and we delete it after the test.
  • Corporate accounts with an administrator on your side.

When data cannot leave the company

The open model runs on your server or in your cloud in the EU. To choose from:

White-tailed eagle
Polish model, SpeakLeash and ACK Cyfronet AGH
PLLUM
Polish model, HIVE consortium commissioned by the Ministry of Digitization
Qwen
Alibaba
GLM
Zhipu AI
DeepSeek
DeepSeek

We select a model for the task and check it on your cases. We run it, tune it and maintain it.

Source: Bielik and PLLuM, ACK Cyfronet AGH ↗ · PLLuM, Ministry of Digitization ↗

Do you have a lot of your own data? We will fine-tune the small model.

  1. 1 Your examples
  2. 2 tuning
  3. 3 test on new cases
  4. 4 model at your place

When you have thousands of similar emails, documents or reports, we teach a small open model based on your examples. It works for you, responds quickly and costs less to maintain than a large model. We measure quality on issues that the model has not seen while learning.

Przemysław and Piotr did it in large programming and consulting companies. Artem did it before and does it today at Syntalith. It's about models on your own infrastructure, tuning and quality measurement.

You choose the protection level during the interview. We sign the data processing agreement before we see any data.Schedule a free analysis →

Custom AI apps

When an off-the-shelf tool does not fit, we build your own.

We build an application with a language model for the work of your team: searching the company's knowledge, case panel or portal. We check the validity of your documents before launch, and the code stays with you.

See AI applications →
net per application, fixed price before contract
from €3,000
from signing the contract to acceptance
4–10 weeks
free prototype on your documents
€0

Questions

  • How do you build an AI knowledge base in a law firm?

    Start with a library of templates and research notes cleared for shared use, with a person responsible for keeping each item current. Knowledge from client files enters the library only as an edited and approved version.

  • Can the assistant use other clients' files?

    No, if the person asking has no access to them. The assistant then shows no content, title, passage or quotation, because a title with a client's name also reveals information.

  • What happens after access to a matter is removed?

    A new search follows the current permissions, also in an open conversation. The firm decides separately whether the user may read earlier answers, and checks that the tool applies that rule.

  • How much does a knowledge base for a law firm cost?

    At Syntalith an AI app on documents costs from €3,000 net. At 300 questions a month of 15 minutes each, the payback is 1.4 months. First check the search and the assistant in your current document system.

Let's talk

Just write, call or choose a date.

We work fast because we hate corporate cotton wool. We don't have salespeople or managers to keep an eye on managers. You talk immediately to engineers who then build your system. We respect each other's time and yours too.

We will accept 3 more companies by the end of the year.

Mon–Fri 9:00–17:00 CET

What our OpenAI and Anthropic partnerships mean for you.

OpenAI makes ChatGPT and Anthropic makes Claude. We belong to the partnership programs of both companies, so we work with their tools every day and learn from the creators themselves.

OpenAI Select PartnerClaude Partner Network
01We will select a tool for the task
We implement both ChatGPT and Claude. We check both on your documents, and you choose the one that makes fewer corrections and saves more time.
02Knowledge straight from the creators
We learn from official OpenAI and Anthropic courses and materials. Your team learns about the features and settings that work today.
03Licenses without our margin
When we roll out ChatGPT, Claude or Copilot, you buy the licences directly from OpenAI, Anthropic or Microsoft and they invoice you. We add nothing to the licence.
04Certified engineers
On the team, we have an AWS certification in machine learning and an Anthropic certification in systems architecture on Claude.

Participation in programs does not mean that OpenAI or Anthropic endorses our services.