AI intake for law firms: the 5:15 inquiry answered, screened and booked into your system
An inquiry that arrives after your receptionist leaves is also calling four other firms, and most of them hire whoever picks up. Your line answers in two rings at 5:15pm and at 2am, asks what your best intake person would ask, runs a first-pass conflict check, books the consult with the lawyer who handles that work, and writes it all into Clio, MyCase, PracticePanther or whatever you run.
What you get
3 things that decide this
- 01Every inquiry answered, phone or web form, day and night, with your screening questions asked by practice area and the routine ones booked while you're in court.
- 02A consult on the calendar and a lead in your own intake system with the recording attached, not a message in an answering service's portal that someone re-keys on Monday.
- 03A first-pass conflict check before the consult is booked, and a hard rule that anyone in distress, under arrest or facing a deadline tomorrow reaches a person now.
From the first ring to a booked consult, and what each step writes back
These are the first two stations of the full law-firm workflow that the intake layer owns. Pick your platform to see the write-back.
Station 01 · The 5:15 inquiry
- Today
- Your receptionist has gone home, the web form sits in a shared inbox, and the voicemail says you'll call back tomorrow. By then the lead has reached the next firm on the list.
- What we automate
- Your line answers in two rings, runs the screening questions you'd ask for that practice area, checks the caller and the other party against the names in your system for a first-pass conflict, qualifies the matter, and books the consult in the right lawyer's calendar.
- What stays human
- Anything urgent goes to a person before the caller finishes the sentence: an arrest tonight, a hearing in the morning, a protective order, anyone in danger. Your line says so and connects them.
Writes to ClioNew contact and matter-intake record with practice area, source and the recording attached; consult on the calendar.
Station 02 · Qualify and route
- Today
- A paralegal decides by gut feel which inquiries the partner sees, or nobody decides until Monday and the good ones have gone cold.
- What we automate
- You get a routing table your intake manager can read and edit: practice area, jurisdiction, matter value band, statute-of-limitations urgency, referral source. Nothing hides in a prompt. Each lawyer sees the right inquiry with the notes already written.
- What stays human
- Taking the case is a lawyer's decision, always. Your line qualifies and books; it never quotes a fee, never advises, and never says you'll take the matter.
Writes to ClioLead stage, assigned lawyer and source written to the record.
Station 03 · Consult booked and confirmed
- Today
- Someone promises a callback, the callback slips, and the caller books with the firm that gave them a time on the spot.
- What we automate
- Slots come from the lawyer's real calendar, the caller gets a text and an email with a name and a time, reminders go out before the consult, and a missed call on a paid lead gets a text back in seconds.
- What stays human
- Reschedules, fee questions and anything the caller wants to argue about stay yours. It proposes; your office decides.
Writes to ClioCalendar entry with the lawyer assigned and the intake record linked.
After the consult come the engagement letter, the matter, the drafting, the deadlines and the invoice. The legal hub walks the whole chain.
Four things the intake layer does, and what it plugs into
After-hours and overflow intake
Evenings, weekends, lunch, and the minutes your front desk is on another call. Your line asks your questions by practice area, handles the inquiry the way your best intake person would, and hands anything urgent to a human immediately.
Screening and conflict rules you can read
Which questions get asked for a family matter, an injury claim or a business dispute; which answers end the call politely; which names get checked for conflicts before a consult is offered. It's a table your intake manager edits, not a prompt we hide.
Web forms and paid leads, answered in minutes
A form submission turns into a call or a text while the visitor is still on your site, and a missed call on a paid lead gets a text back in seconds with a slot. Speed is the whole point of intake: the lead is comparing firms right now.
Write-back, not a message
A booked consult means a lead in your own system with the recording and the screening answers attached, whether that's Clio Grow, MyCase, PracticePanther, Smokeball, Lawmatics or something you built. We confirm exactly what your account exposes during the audit.
Smith.ai, Ruby and Lawmatics are good at what they were built for. Here's where a custom intake layer starts.
A staffed legal answering service takes a good message and is polite at 9pm. An intake CRM with automation follows up on the leads you enter. Both are the right answer for a small firm that just needs the phone picked up and the follow-up not forgotten, and we'll say so on the audit call.
You outgrow them at three points: when intake has to run your screening and conflict rules rather than a generic script, when a booking has to land in your practice management system without someone re-keying it, and when you run more than one practice area or office on one number. That's where we build, and the intake layer is written around your matters, your system and your rules rather than configured from a menu.
- 01Your screening and conflict rules, readable and editable by your intake manager.
- 02Booking write-back into your practice management system, with the recording attached.
- 03Your number, your recordings, your data, and a named engineer when the line matters most.
Get a 2-minute demo call from our AI
Leave a mobile number. A person checks the request, then our AI calls you and plays your after-hours line: you're the caller with a car-accident claim at 5:15pm. It asks the screening questions, checks for a conflict, and books the consult. Then it texts you what it would have written into your intake system. It's one part of the build; hear that part first.
Where your clients' information travels is a design decision we make first, on paper, with you
In United States v. Heppner (S.D.N.Y., February 2026) a court held that material a litigant ran through a consumer AI tool wasn't privileged, because that tool's published terms allowed disclosure and training on inputs. Whether an enterprise tool with no-training terms comes out differently was left open, and we don't treat left open as safe.
So every system we build for a firm starts with a one-page map of where client data goes: which vendor, which region, what's logged, what's retained, and whether a private deployment is required by your clients' own obligations. ABA Opinion 512 makes vetting that part of your duty; we'd rather you vet it before the pilot than after.
- 01Access scoped to the matter, never firm-wide.
- 02Written no-training terms you can produce on request, and every vendor in the chain named as a recipient.
- 03Recordings and transcripts retained on your terms, in your region, and deleted on your schedule.
“They will treat your vision like their own and build it that way.”
Ron Klabunde · Founder, SmartREI ↗
“Their attention to detail, quality of employees, and work ethic were outstanding.”
Nicolas de Quesada · CEO, Lexpair
Some of the systems we have shipped
- AuditFree. We read last month's inquiries by hour, source and outcome, and listen to how the line is answered today.
- DiagnoseWe map the path into your practice management system and sit with your front desk and billing for an afternoon.
- BuildFixed price from the diagnostic. Tested on your real matters and real templates, under NDA.
- RunMonitoring, a named engineer, and the first two months of maintenance free.
Best fit: five or more lawyers, a practice management system you've outgrown in places, and someone who owns intake or billing. Not a fit yet: a solo who needs the phone picked up, and we'll say so. You can stop after any stage; the audit note is yours either way.
Before you book
01Can an AI intake line create an attorney-client relationship by accident?+
That's the risk we design against first. Your line identifies itself, collects facts and books a consult; it never gives legal advice, never quotes a fee, and never says the firm will take the matter. Those rules are written into the screening table your intake manager can read, and the disclaimer language is yours. California's 2026 guidance is explicit that a lawyer can't let an AI system take actions a lawyer must take, and intake is built to respect that line.
02What happens when the caller is in crisis or under arrest?+
A person takes the call, immediately. Urgent triggers are a short list you write: an arrest, a hearing tomorrow, a protective order, anyone in danger. Your line recognises them, says it's connecting them, and rings your on-call number. If nobody picks up, it escalates by your rules rather than taking a message and hoping.
03Does it do a real conflict check?+
A first-pass one: it checks the caller, the other party and any names given against the contacts and matters in your system before a consult is offered, and flags a possible match for a human to clear. Your full conflict check stays with your conflicts process, because that's a judgement, not a lookup.
04We use an answering service today. Why change?+
Maybe don't. If your volume is low and the service takes a good message, keep it, and we'll tell you that on the audit call. Firms switch when messages pile up unread, when leads hire elsewhere before the callback, or when every message has to be re-keyed into the intake system. That's when a line that screens, books and writes back pays for itself.
05Will it book straight into our practice management system?+
Yes, to the depth your account exposes. Clio, MyCase, PracticePanther and Smokeball each publish an API that covers contacts, intake and calendars to different depths, and we confirm exactly what yours allows during the audit. Where the API stops, the line writes a structured intake your staff can accept with one click rather than re-type.
06Where do the recordings go?+
Where you decide. Retention, region and deletion are set in writing before the first call is recorded, every vendor in the chain is named as a recipient, and the terms include no training on your data. Recordings attach to the lead in your system; nothing sits in a portal you don't control.
07What does the free audit look at?+
Last month's inquiries by hour, by source and by what happened next; how the line is answered today; the manual touches between a good inquiry and a signed engagement letter; and where client data would travel in any automation. You get a one-page note you can hand to another vendor. Build pricing is fixed after the diagnostic.
A senior engineer, not a sales rep
Abdul Basit founded Hashlogics in 2017, and the team runs from Lahore with a US LLC. Clients rate the work 5.0 on Clutch, and in 2026 it was named Best AI-Native Software House of the Year at TechNova. Lexpair, an AI legal lead-generation platform, is one of the systems we built and can show you.
Your audit call is with an engineer who has read intake logs, matter lists and billing exports like yours. Bring last month's numbers if you have them, and we'll work from those.
- NDA before the first conversation.
- No pitch on the call. A note you could hand to another firm.
- Fixed price after the diagnostic, so the number isn't a guess.
Go deeper
- AI, automation and custom software for law firms →The whole chain, from the 5:15 inquiry to the paid invoice.
- Document automation for law firms →What happens after the consult: the engagement letter and the first draft.
- Best AI intake software for law firms →The packaged tools, ranked, and where custom fits.
- How fast should a law firm respond to leads? →The first five minutes, and what they're worth.
- Is AI intake safe for a law firm? →Privilege, confidentiality and the unauthorised-practice line.
- The 5:15 inquiry: the law firm call nobody answers →The call after hours, and the firm that got it.
