AI for law firms

Why AI in a law firm starts with the case files, not with an "AI lawyer"

Law firms are offered AI from the spectacular side: a chatbot answering clients, "AI that writes pleadings", a tool that "predicts the judgment". The common problem with those projects is that their output is hard to check — and in a lawyer's work an output that cannot be verified efficiently does not save time, it moves the time to later corrections. In a law firm's day-to-day work it is clear where time actually goes.

It goes into reading. In a case with several volumes of files, someone has to establish who said what and when, and where the documents contradict each other; a three-hour meeting recording has to be listened to in order to pull three sentences out of it; in the court portal every case has to be clicked into every day to see whether a new document or a date has appeared. These are text- and audio-based processes on material the firm already lawfully holds, with rules that can be written down and a result the lawyer can check against the source.

That is why we start the first AI project in a law firm where the effect shows soonest: the system prepares the material the lawyer starts from — findings, summaries and deadlines, each linked to its source. Legal assessment, filings to the court and client conversations stay in the lawyer's hands.

What we actually implement in law firms

• Document and evidence analysis. Reading, classifying and cross-referencing large sets of pleadings, contracts and case files: extracting facts, dates, amounts and parties, pointing to the places where documents contradict each other, and summaries in which every sentence refers to its source page. The AI model proposes, the lawyer checks and decides. The link to the page of the file makes verification easier, but the lawyer still checks accuracy against the source, the context and whether anything significant has been left out; how much of the source needs reading depends on the case.
• Transcription and analysis of recordings. Transcription of hearings, client meetings and recordings from the case file, with the speakers separated and labelled. With video material from the file the system works on the labels a lawyer assigns — who is who in the first minutes — and groups the segments of that recording by those labels, preparing time-coded excerpts for the lawyer to check and for pleadings. This is assistance in reviewing material the firm already lawfully holds, on its own legal basis: the system establishes nobody's identity, matches nobody against external sources, creates no reusable biometric templates and is not a face-recognition service.
• Information maps for litigation. An organised map of the facts, people, documents and dates in a case, with the links between them. With it, the case can be reviewed without re-reading it before every pleading. The map is built from the file, each item points to its source, and the whole map can be exported into the system in which the firm keeps its documents.
• Automatic checking of cases in the Polish courts' information portal. Our own portal connection (an MCP server: software built on an open standard for connecting AI assistants to systems), delivered only as part of an AI implementation in the firm — never as a separate product. It connects the firm's assistants and automations to the Portal Informacyjny Sądów Powszechnych through the firm's own account: case status, new documents, hearing and session dates reach the assistant, the calendar and the document workflow without clicking into every case every day. The integration only reads: it sees exactly what the account's user sees, does not download data in bulk, does not receive served documents and does not file pleadings, and the firm remains the holder of the account and the access rights. What the portal exposes, and what cannot be automated, is described in our article on automating case monitoring in the courts' information portal.
• Drafts citing the firm's own precedents. Draft pleadings that cite earlier pleadings, opinions and rulings from the firm's archive — showing where every argument comes from — instead of an assistant that "knows everything" and cannot say from where.
• Intake, deadlines and anonymisation. Preliminary ordering of client enquiries before a lawyer's call; automatic calendar entries for the dates in pleadings and the portal, with reminders; and anonymisation of documents before anything leaves the firm — the model receives only what a given step needs.

The common denominator: the lawyer approves the result, the system prepares it. Which processes qualify for this kind of automation at all — the five conditions a good candidate must meet — is described on the AI automation page; in a law firm those conditions are checked exactly the same way, only with a stricter requirement of verifiability.

Data, GDPR and the AI Act

Case files, recordings and video are the personal data of parties, witnesses and third parties — often of special categories. The firm processes them on its own legal basis: it determines the Article 6 GDPR basis and, where the material contains special categories of data, the Article 9(2) condition — in litigation usually the establishment, exercise or defence of legal claims (point f). We work with the firm and its data protection officer: they determine the legal basis, and we build the system exactly to that determination. The data stays in the firm's infrastructure or with a provider with an EU processing region that the firm itself chooses, with training switched off and a data-processing agreement in place; the model receives the minimum a given step needs, anonymised wherever possible.

Which AI Act obligations apply to a given tool depends on the firm's role, the system's intended purpose and its risk category: telling people they are dealing with a system (Article 50, where the system interacts with people), human oversight (Article 14 for high-risk systems), no prohibited practices (Article 5). We treat them as the firm's decisions that we build to: a register of systems, a record of the system's actions, and a lawyer approving the results. Approving every result this way is our own rule regardless of whether a provision requires it. The lawyer or the data protection officer classifies the system and assesses its impact, and we implement the controls that follow — how we divide that work is described on the AI Act technical compliance sprint page.

What we guarantee your firm

• Legal judgement and the signature stay with the lawyer. The system we implement prepares the material — sourced findings, summaries, draft pleadings — while the legal assessment, the strategy and the signature belong to the lawyer. That way every result is owned by a named person who has checked it.
• Filings and served documents are handled by the representative. The court-portal integration reads and flags changes. Receiving a document in the portal has procedural effects, and filing a pleading is an act of the representative — so a person always performs both, deliberately and at a moment of their choosing.
• Every result can be checked in the file. We build tools that point to the source of every finding, not systems that predict judgments or assess the credibility of witnesses. The lawyer gets material for their own assessment, and responsibility stays where it belongs.
• Recording analysis without biometric surveillance. The recording analysis we implement assists the review of material the firm already holds and works on labels assigned by a lawyer. We build it without remote biometric identification, without face recognition and without inferring people's emotions or characteristics.

How we work

As in every project: we pick one process and measure one indicator before we start, for example hours from receiving a file to a ready summary with references. Then we run a pilot on data samples, followed by a trial run on real data: before switching over, the system runs alongside the current way of working for a while. At first the system prepares and a lawyer approves every result. The full course — four phases and what you get at the end of each — is described by the delivery methodology, and the full scope of the service, from the process audit to maintenance, by the AI implementation page.

A separate topic that comes back in every law-firm conversation is data: professional secrecy, evidence, recordings. Where data goes when we integrate an AI model, and what to ask any provider, is set out on the security and GDPR page, and the commitments that apply to every project in our standards.

What it costs

Three things drive the cost: the number of systems to connect, the state and volume of the material, and how reliable the results must be, that is, how rarely they may be wrong. The number of lawyers matters less — what counts is whether the files are digital and orderly or go through the scanner afresh for every case. We set the scope and the price after a first conversation; all the components, maintenance included, are broken down in our article on what an AI implementation costs.

Frequently asked questions

Where should a small law firm start with AI?

With one kind of material you already have and currently read in full: the files of one category of cases, recordings of client meetings, or the daily check of the court portal. A good first project has a number measured before the start — hours to prepare a summary of a case file, the number of cases checked by hand in the portal — and a result with source links that help the lawyer check the findings, their context and significant omissions. We do not start with an assistant that "answers everything"; we start with a process whose result can be checked against the source.

What happens to client data and evidence?

It stays where the firm decides: in its own infrastructure, or with a provider whose processing region is in the European Union, with training on your data switched off and a data-processing agreement in place. Personal data in case files, recordings and video is processed by the firm on its own legal basis — in litigation that is usually the establishment, exercise or defence of legal claims, and for special categories of data the condition in Article 9(2)(f) GDPR — and it is the firm, not us, that determines that basis. Before the integration, not after it, we settle together which data leaves the firm at all, to what extent and after what anonymisation. The rules, and the questions to put to any provider, are set out on our security and GDPR page.

In what form do we deliver the court-portal integration?

As part of an AI implementation in the firm. We configure the connection to the Portal Informacyjny Sądów Powszechnych (the Polish courts’ information portal), an MCP server, together with the firm’s assistant, calendar and document workflow. The reason is practical: the integration alone gives the firm a list of changes in its cases, and the value appears when that list reaches the assistant, the calendar and the document workflow that we configure and test together. The integration runs on the firm’s own account and sees exactly what a user logged into that account sees.

What does automating hearing and meeting recordings require?

A lawful recording. Whether the recording could be made at all — the consent of the meeting’s participants, the court’s permission to record, the electronic record from the portal — is the responsibility of the firm and its lawyers; we work on material the firm already lawfully holds. Technically it takes audio of reasonable quality and, for video, a few minutes in which a lawyer labels who is who. From that point the system separates the voices, groups statements and segments by the labels the lawyer has assigned, and prepares excerpts with timestamps showing where they occur in the recording for the lawyer to check. It establishes nobody’s identity, matches nobody against external sources and creates no reusable biometric templates.

How is the AI’s output verified?

The way a trainee’s work is: every finding, date, quotation and summary points to the page of the file or the minute of the recording it comes from, which makes verification easier: the lawyer checks each finding against the source, its context and any significant omissions, and the amount of reading required depends on the case. In the trial run we work in parallel — the team does what it did before, the system prepares its own version — and we count how many findings were correct, what errors occurred and what they cost. Only those numbers decide which tasks may go on without every result being approved. In litigation, a lawyer approving every result usually stays in place for good.

How much does an AI implementation in a law firm cost?

Three things drive the cost: the number of systems to connect — the practice-management software, email, the calendar, the document storage system, the court portal — the state and volume of the material, and how reliable the results must be, that is, how rarely they may be wrong. The number of lawyers matters less than whether the files are digital and orderly or go through the scanner afresh for every case. Maintenance is a separate line: usage-dependent fees and periodic tests after model version changes. We set the scope and the price after a first conversation and a short look at the material; the cost components are broken down in our article on what an AI implementation costs.