How does a law firm use intusell? A daily operations guide

In the main article, you trained the intusell AI: you uploaded the knowledge base, set up consultation appointment types and the lawyers' working hours, and configured the persona and legal boundaries. Training was a one-time setup. Now the real work begins: how does a law firm use intusell, that is, how does law firm intusell usage work in daily operations? This article shows, step by step, what the assistant you trained actually does in the field over a working day — from the incoming WhatsApp message to the consultation appointment, from follow-up to handing off to a human.

This article is the second part of the law section of our sector-based "how to train your AI" series. The first part, how to train the intusell AI, covered the setup; this one covers turning that setup into daily operations.

Quick answer

A day in the flow

A firm that has set up intusell has a typical day that looks very different from before. In the past, the assistant would arrive in the morning and sift one by one through dozens of unread WhatsApp messages, separating which was a real request and which was an ad. Now the messages that came in overnight are already answered, the requests are pre-classified, and consultation appointments are created. The backbone of a day works like this:

The team is no longer busy sifting through messages and screening "is this a fit or not", but instead deals with conversations that genuinely require a lawyer — the ones that call for a legal assessment.

Who is it for?

This usage model makes the most sense especially for these firms:

• Firms that receive heavy first inquiries via WhatsApp and Instagram — those who can't keep up with dozens of "I want a consultation" messages a day.
• Firms with low consultation conversion — those losing prospective clients to another firm because the response comes back late.
• Firms that lose after-hours demand — those who respond late to urgent questions that come in during the evening and on weekends.
• Firms that have to separate ads from real requests — those whose inbox is a mix of spam and genuine prospects.

If you have an inquiry volume a single assistant can't keep up with, intusell works like an initial-meeting coordinator with clear boundaries that handles those inquiries — but it doesn't replace the lawyer.

The most important boundary: the AI does not give legal advice

For a law firm, this is the rule that comes before everything else. intusell does not give legal advice, predict case outcomes, or suggest strategy on a concrete matter. This is both a professional boundary and a way to prevent a wrong steer from putting the client and the firm at risk.

In practice, what the AI does and doesn't do breaks down like this:

When a client asks a concrete question like "Can I object to this rent increase?", the AI doesn't list possible answers; it says "This depends on the details of your case; let our lawyer assess it in the consultation" and routes to an appointment. Wherever it doesn't know or interpretation is required, it honestly states its limit and hands off to the lawyer. We explain in detail how you set up this boundary during training in the how to train the intusell AI article.

Incoming request: the client asks, the AI clarifies and routes

The flow starts when a prospective client sends a message. Imagine someone writing on WhatsApp, "My landlord has filed an eviction case, what do I need to do?" The AI reads this message, pre-classifies which area of law the request falls under (here, real estate/tenancy law), scans the firm information in your knowledge base, and steers the client to the right step — a consultation appointment.

Two points are critical. First: the AI does not interpret the matter. To "Is the eviction justified?" it doesn't make a for-or-against assessment; it leaves the situation to the lawyer and routes to the appropriate consultation appointment. Second: whatever language the client writes in, the AI replies in that language — a practical convenience for firms with foreign clients.

If during training you added the rule "before the appointment, ask about the subject and urgency, but don't give a legal opinion," the AI first clarifies which area the subject falls under, any hearing/notice date, and the urgency status. We cover separately how all these channels come together in a single inbox in the Instagram and WhatsApp consultation automation article.

Booking a consultation: slot, duration, and conflict prevention

When the client asks for a meeting, the AI doesn't pull a time out of thin air. It looks at the three things you defined during training: the duration of the consultation type (for example, "Initial Meeting 45 min"), the lawyer's working hours, and whether that slot is taken. If it finds a suitable slot, it creates the consultation.

Here the most critical safeguard is conflict prevention: two meetings cannot be entered for the same time. Before creating an appointment, intusell checks your working hours and existing appointments; if a conflicting slot is requested, it doesn't open the appointment. Cancelled or no-show (missed) appointments free the slot again in this check. So the nightmare that small firms experience most often — a lawyer being called into meetings with two clients at the same time — disappears.

Every consultation has a status, and its lifecycle is clear:

scheduled (planlandı)
  → confirmed (onaylandı)
  → attended (görüşme yapıldı)
veya
  → cancelled (iptal)
  → missed (gelmedi)

You'll find detailed instructions on how to set up consultation types, durations, buffer times, and calendar sync in the law firm consultation appointment automation article.

Reminders, the document list, and reducing no-shows

The most expensive thing in a firm is a client who doesn't turn up: a consultation hour left empty is the lawyer's unbillable time. intusell reduces this with automatic reminders.

For every consultation appointment, two reminders are scheduled:

• 1 day in advance: a message along the lines of "You have a consultation appointment tomorrow at [date time]". If you defined it during training, this message also includes the list of documents the client should bring to the meeting (for example, the contract, the notice, ID) — so the meeting doesn't go to waste.
• 2 hours in advance: a short reminder along the lines of "You have a meeting today at [time] — 2 hours to go".

The reminder goes through the channel the client wrote on; if that channel is unreachable, SMS kicks in, and if that fails too, email. The message contains a one-tap cancel/reschedule link, so the client can let you know in advance that they can't make it and the slot doesn't go to waste. If you want to turn off the reminder for a specific appointment (reminders_enabled), you can do that per appointment too.

If the client still doesn't turn up, you mark the appointment missed; intusell automatically re-offers the freed slot to suitable ones among the most recent in-follow-up WhatsApp prospects (this re-offer currently goes via WhatsApp) and triggers a follow-up flow. So a no-show meeting becomes not a lost hour but an opportunity that gets reassessed.

Case status queries: a summary yes, interpretation no

Your existing clients most often write to ask "What's the status of my case?" intusell handles this question with balance: it shares the summary status entered into your knowledge base and leaves the legal interpretation to the lawyer.

In practice, the AI relays objective information you've recorded in the system, like "The hearing date for your case is set for March 14." But on a question requiring an assessment, like "What happens at this hearing?" or "Will we win?", it stops and escalates the conversation to the lawyer. The client gets a quick summary, while the legal interpretation always comes from the lawyer.

Consultation fee and boundaries

For a law firm, the fee is a sensitive topic: the fixed consultation fee and the case-specific attorney's fee are different things. The AI holds this line:

• It can share the fixed consultation/initial-meeting fee from the knowledge base (per your firm policy).
• For case-specific amounts like the attorney's fee, it routes to an appointment by saying "this becomes clear in the meeting, based on the scope of the case".
• Phrases like "you'll definitely win", "guaranteed outcome", or "you'll get this much in damages" are both professionally improper and constrained so the AI won't produce them; the safeguard layer also scans for and flags such promises.

So rather than inventing a figure it isn't sure of, the AI steers toward the right step — the consultation or the lawyer. At no stage does intusell collect the fee itself; the firm is the one providing the service and issuing the invoice. For product and pricing details, you can check the solutions and pricing pages.

Confidentiality, KVKK, and the attorney-client relationship

In a law firm, incoming information is often sensitive and falls under attorney-client confidentiality. intusell safeguards this at three points:

1. Explicit consent record: The client's explicit consent is recorded along with its time and type (kvkk_consent_at / kvkk_consent_type).
2. Sensitive-field control: Fields like case notes / matter summaries are flagged with the highest sensitivity; they aren't saved automatically and require manual confirmation.
3. Encrypted storage and masking: Personal data is end-to-end encrypted; PII masking is applied to voice recordings. Attorney-client confidentiality is preserved with these layers.

This makes it easier, in the event of an audit or objection, to answer the question "what did the client consent to, and when?" with evidence; at the same time it prevents sensitive case information from being recorded haphazardly.

Following up a quiet client: proactive follow-up and CRM

In a firm, most business is lost with prospective clients who say "let me think, let me ask my spouse" and disappear. intusell doesn't forget these prospects. A proactive follow-up message goes to a prospect who got the information and then went quiet; interest is kept alive. Every conversation is logged to the CRM, so the prospect's history, which subject they came with, and what stage they're at stay on record.

This way, when the team sits down to operations in the morning, it's clear which prospect is hot and which is waiting on follow-up. There's no need to keep a manual reminder list. There is no managed waitlist; the system only reaches back out to suitable in-follow-up WhatsApp prospects.

Client line: the law pipeline

Every prospective client moves along a client line (pipeline), and as the AI conversation develops it moves the prospect to the right stage. The stages of a typical law line can be thought of like this:

Yeni Talep / Başvuru
  → Danışma Randevusu Alındı
  → İlk Görüşme Yapıldı
  → Vekâlet / Teklif Sunuldu
  → Vekâletname Alındı (kazanıldı)
veya → Vazgeçildi (kaybedildi)

Thanks to this line, you can see at a glance which prospect only got information, which got a consultation, and which is waiting on a decision to engage. When the AI creates a consultation appointment, it automatically moves the prospect to the "Consultation Booked" stage.

Handing off to a human: working modes

You decide how autonomously the AI works. There are three working modes:

In hybrid mode, the AI hands a question requiring a legal opinion, a possible conflict of interest, or an urgent situation (for example, an upcoming hearing or a detention) off to the lawyer. At the moment of handoff, the entire conversation history is in front of the lawyer; the client doesn't have to explain the matter from scratch. You can change the mode at any time.

What it isn't

To put intusell in the right category, let's clarify what it isn't:

• It isn't a lawyer or a legal advisor. It doesn't give legal advice, doesn't state case outcomes, doesn't suggest strategy; it leaves the concrete legal question to the lawyer.
• It isn't a court case-management system. It doesn't carry out official case-file actions; it's the consultation appointment, communication, and client-coordination layer.
• It isn't a collections or accounting agent. The firm is the one providing the service and issuing the invoice; intusell is not a seller or intermediary.
• It isn't a law-specific priced product. The pricing model is based on messages and voice minutes, and doesn't change by sector. The consultation appointment module can be enabled on any plan.

So you don't start with the wrong expectations, let these boundaries be clear from the outset.

Frequently asked questions

Does the AI give legal advice?

No. The AI does not comment on case outcomes, loss of rights, or legal strategy. It only provides information about procedure, required documents, the consultation fee, and how the firm works; for concrete legal questions, it routes the client to a lawyer and a consultation appointment. The firm is always the one providing the service.

Does the AI create the consultation appointment on its own?

Yes. The AI clarifies the subject of the request and creates a consultation appointment based on the lawyer's working hours and open slots. Double-booking the same time is prevented by the system. In a conflict of interest, an urgent matter, or a complex situation, it hands the conversation off to the lawyer.

What happens if a client asks "what's the status of my case?"

The AI only shares the summary status entered into your knowledge base (for example, "the hearing date is set", "the petition has been filed") and leaves detail and interpretation to the lawyer. It does not make a legal assessment of the case file; it escalates the conversation to the relevant lawyer.

Which channel do hearing and appointment reminders go through?

First through the channel the client wrote on (WhatsApp, Instagram, Telegram, Messenger); if that's unreachable, then SMS, and if that fails, email. The client doesn't need to install a new app; they receive the reminder on their existing channel.

Does the AI quote the consultation fee?

It depends on your firm policy. In a typical setup the AI shares the fixed consultation/initial-meeting fee from the knowledge base; for case-specific amounts like the attorney's fee, it says "this becomes clear in the meeting" and routes to an appointment, never inventing a figure.

How are client information and confidentiality protected?

Client information is end-to-end encrypted; explicit consent is recorded with its time and type. Sensitive case notes are flagged with the highest sensitivity and are not saved automatically. Attorney-client confidentiality is preserved; when needed, the conversation is handed off to the lawyer with the full chat history.

Next step

If you haven't trained your assistant yet, start first with the how to train the intusell AI article — the foundation of this operation is set up there. If you want to go deeper on the channel side, you can move on to the Instagram and WhatsApp consultation automation article, and for the details of the appointment engine, the law firm consultation appointment automation article; you can see the solution built for law firms on the law firm page, and review the whole series on the all articles page.

If you're curious how the same logic is set up in another regulated field with an "it doesn't give advice" boundary, the clinic AI training article offers a good comparison; in tourism, the flow is in the tour agency AI training article.

To see live how it would work in your own firm, request a demo or write directly to hello@intusell.com. In a 20-minute session, we open your inbox together and test the first consultation appointment in the system.