Industry offer · Law firm

AI for lawyers and law firms - with professional secrecy

SAIE for law firms is an AI environment in which case files and client data stay under the firm’s control, and answers are based solely on sources, with a citation. AI for lawyers with no invented case references and no case files in someone else’s chatbot

Polish courts have already seen filings with rulings made up by AI. We describe who is liable and how to prevent it in Made-up court rulings. Who is liable when AI gets it wrong?

Why now

2026 brought lawyers three signals at once: § 23e of the Code of Ethics for Advocates (Zbiór Zasad Etyki Adwokackiej) of June 2026 on technology tools, the Act on Artificial Intelligence Systems - with inspections and penalties from 28 October 2026 - and the recommendations of the judges’ association “Iustitia” ruling out processing case data in commercial chatbots. KIRP (National Chamber of Legal Advisers) also issued AI recommendations (May 2025). The question is no longer “whether” but “how” - and that “how” must answer where the data is, who has access to it and which tool processed it when

Three people who need to say yes

Managing partner - more pleadings and cases without higher costs

Lead lawyer - pleadings and deadlines under control, zero invented judgments

Firm compliance / IT - professional secrecy enforced technically

Business scenarios

Legal answers based solely on sources

Knowledge and documents

TWIN:DESKNEW · SAIE PANTERA

Problem: Invented case references and non-existent judgments in material prepared by AI

How it works: Answers only from the central RAG knowledge base, from a selected set of case files and case law; source preview; the Knowledge Gap Register flags a missing basis. Agentic RAG asks again in another round when something is missing, and TWIN:INDEX searches long documents by chapter

What you gain: Every claim has a source you can click, and a missing judgment in the base is a message, not an invented case reference

Assistant for drafting pleadings

Process automation

TWIN:DESK

Problem: Every pleading is written from scratch

How it works: A case workspace with the files, timeline and correspondence; a local agent reads Outlook mail without copying it to the central base and prepares a draft pleading for review

What you gain: The draft is built from the case files and correspondence, so the lawyer starts with a substantive review, not a blank page

Automatic tracking of procedural deadlines

Process automation

TWIN:DESK

Problem: Procedural deadlines are tracked by hand in several places at once

How it works: Schedules, a “Morning Triage” that sets the day’s priorities, and a Kanban task manager with dates

What you gain: One view of deadlines for all cases, prioritised for today - the risk of missing a deadline no longer depends on a single calendar

Automatic time reporting

Analytics and reporting

TWIN:DESK

Problem: Time recording for cases is late and inaccurate

How it works: Automatic timesheets based on system activity and the calendar

What you gain: Time spent on a case is recorded as you go - the client invoice is complete, not reconstructed from memory

A confidential AI environment for case files

Security and sovereignty

TWIN:DESK + PROXY:AINEW · SAIE PANTERA

Problem: Professional secrecy rules out processing case files in commercial chatbots

How it works: Confidentiality mode and permanent marking of case files as confidential; confidential data blocked from routing to cloud models; deployment on-premises in the firm’s infrastructure. Translation on local models, with a terminology glossary and a DOCX file that keeps its layout

What you gain: The line between a general question and case data is guarded by the architecture, not by the lawyer’s attention “mid-sentence”

Documented use of AI in cases

Compliance and oversight

PROXY:AI + CDF

Problem: At the client’s request, the advocate indicates the AI tools used in the case and their purpose (§ 23e of the Code of Ethics), and the firm must be able to show this

How it works: An immutable log of model use; AI Disclosure Injection that marks AI-generated content; an AI use policy and an agent register (CDF-F2)

What you gain: The firm can show the client and the bar council which tool processed the case data, when and why

Evidence

Article “Does a lawyer need sovereign AI?” (28 August 2026)

Read →

On-premises deployment, local agent for Outlook

How we start

A demonstration on an anonymised case of your firm - pleading assistant, source verification and an AI use log in one environment

Questions decision-makers ask

Does data leave the EEA?

Not unless the firm decides so. TWIN:DESK runs on-premises or in a cloud with data located in Poland or the EU, and PROXY:AI lets you allow only models that run locally or in the EU

Will our data be used to train models?

No, if the firm uses local models or providers whose contracts exclude training on client data. PROXY:AI lets you allow only such models and masks personal data before a query is sent

Does the tool provide adequate protection within the meaning of § 23e?

The assessment is up to the firm. SAIE gives it the basis for one: control over data location, case-level permissions, a log of who processed documents and when, and documentation to demonstrate due diligence

Can AI prepare a draft pleading?

Yes, as a draft for review. However, the rules of professional ethics for advocates (§ 23e ZZEA) require the advocate to assess and verify the result personally and to remain personally responsible for the content of the pleading, and the recommendations of KIRP (National Chamber of Legal Advisers) warn legal advisers against over-reliance on AI. TWIN:DESK prepares the draft from the case files, timeline and correspondence, so the lawyer starts with a substantive review, not a blank page

Can a lawyer use ChatGPT?

Yes, for general questions and fully anonymised material, if used deliberately. Case data, however, should not go into a consumer service: § 23e ZZEA (Code of Ethics for Advocates) and the recommendations of KIRP (National Chamber of Legal Advisers) protect professional secrecy, and such an account offers neither a data processing agreement nor a record of who processed the data and when. In SAIE the best models remain available, but behind the PROXY:AI gateway, which does not let confidential data out to the cloud. We write more about this in the article “Does a lawyer need sovereign AI?”

All questions

Other paths: Finance and professional services

Finance and insurance

AI under KNF (Polish Financial Supervision Authority) supervision: every decision has an author, data and an audit trail

Accounting firm

AI that reads invoices, tracks deadlines and keeps client data separate

Business consulting

Faster deliverables, expert knowledge retained in the firm, client data kept separate