An AI Receptionist that books, reschedules & cancels appointments — 24/7 — and writes them straight into
Lawmatics.
Plugs into your website and phone line. Voice in 30+ languages. Live by tonight, booking customers by tomorrow. No Zapier, no n8n, no code.
Talk to the agent on the left. Watch the booking appear on the right.
This is the same agent shape you'll deploy. Ask it about a haircut on Tuesday, a reschedule, or a cancel — it'll write the appointment straight into the calendar.
FAQ — Lawmatics integration.
Does this actually work with my Lawmatics account?
Will it create duplicate Contacts in Lawmatics?
Can it route different intakes to different attorneys?
Where do the consultations actually live, calendar or Lawmatics?
Can it cancel or reschedule a consultation from a phone call?
Does it open a matter, or just a contact?
What if a caller has two upcoming consultations in Lawmatics?
Does it handle timezones correctly?
Does it create new matters at the right pipeline stage?
AI Receptionist Call or AI Receptionist Web). Your flow decides which pipeline transitions, which automations, which workflow trigger. AnyCRM doesn't try to encode policy that will drift out of date the moment your firm changes.How does the conversion tracking work?
What about my existing website intake forms? Do they go through the same pipe?
How long until it's actually capturing intakes into Lawmatics?
Captures the intake as a Lawmatics contact, opens the matter, books the consultation, and feeds one unified conversion pipe for your website forms AND your AI Receptionist.
Every caller who lands on the line becomes a Lawmatics contact (with a linked matter, the right practice area, the right responsible attorney, and original-source attribution). When they want a consultation, AnyCRM creates a native Lawmatics appointment on the matched attorney's calendar. AND the same lead event flows through one unified pipe (with the same shape, same source attribution, and same server-side conversion path used by your website forms) so your Lawmatics intake pipeline AND your Google / Facebook / LinkedIn Ads both stay in sync.
Every caller becomes a Lawmatics contact, not a missed intake
The AI Receptionist captures name, email, phone, practice area, opposing party, jurisdiction, and the caller's account of the situation. Then AnyCRM writes the record into Lawmatics as a contact with a linked matter, the right responsible attorney, lead status, and intake-pipeline stage attached DURING the call.
Books consultations as native Lawmatics appointments
The consultation lands as a Lawmatics appointment with the matched attorney as host, the prospective client as invitee, and the matter linked. So it shows on the matter timeline and the attorney's calendar exactly the way Lawmatics expects — and Lawmatics' Google/Outlook calendar sync fires automatically.
Sends the lead event straight to your CRM. You decide what happens next.
AnyCRM does not pretend to know your intake-conversion rules. Every contact-create and every consultation-book sends a lead event straight to your CRM (with source: "AI Receptionist Call" or source: "AI Receptionist Web") where YOUR intake automations take over. Move the matter through the pipeline, fire the conflict check, send the engagement letter, route the workflow. We set up the receiving end inside your CRM for you during onboarding, tuned to the practice areas you handle and your firm's configuration. AnyCRM doesn't get in the way of policy you've already encoded.
One conversion pipe for your website forms AND your AI Receptionist.
Most law firms run two completely separate conversion-tracking stacks: one for the website (intake forms, chat widgets, page-load pixels) and a totally absent one for the phone and the AI Receptionist. So Google Ads and Facebook Ads only learn from web form-fills, the bidding optimises for the wrong audience (often tire-kickers comparing five firms), attribution is broken, and analytics double-count or miss real consultation requests entirely. AnyCRM closes that gap by running BOTH surfaces through a single conversion pipe.
1. Capture
A lead arrives either through your website intake form / chat widget OR through the AI Receptionist on phone / chat. Either way, AnyCRM produces the same clean lead-event shape, tagged at source with either AI Receptionist Call, AI Receptionist Web, or your website's form identifier. One vocabulary across both surfaces.
2. Deliver to your CRM
AnyCRM sends the lead event straight to your CRM, into the receiving flow we wired up for you at onboarding. Your intake automations decide what happens next: which pipeline stage, which conflict check, which engagement-letter template, which attorney's docket. You don't have to maintain two sets of rules. Web leads and AI Receptionist leads both arrive through the same door.
3. Fire server-side conversion to your ad platforms
The same lead event fires server-side into Google Ads, Facebook Ads, and your analytics platform, using the origin of the domain you registered with AnyCRM. Server-side means the conversion can't be blocked by ad-blockers, doesn't degrade under iOS / Safari tracking restrictions, and lands with full attribution context.
4. Optimise, attribute, report
Because website conversions AND AI Receptionist consultations flow through the same pipe with the same source taxonomy, your Google Ads bid strategy now optimises against real signed engagements (not just form-fill noise), your Facebook Ads campaigns see the high-intent traffic that picks up the phone at 9pm, your analytics platform sees a single unified funnel, and attribution stops fragmenting between web and voice.
- Higher ROAS. Ad bidding optimises against actual consultations booked, not against the noisy subset of leads that happen to fill a form.
- Lower ad costs. Once Google Ads and Facebook Ads learn what a real prospective client looks like, they stop spending against lookalikes of low-quality form-fills.
- Enriched analytics. Every intake surface (web form, web chat, phone call, AI Receptionist chat) feeds the same event shape into your analytics, so funnels are complete instead of half-blind.
- Correct attribution. A caller who first saw a Google Ad for "divorce attorney near me," then visited the site, then phoned three days later gets attributed end-to-end. Voice traffic stops being invisible to your marketing stack.
- One source of truth for intake policy. Your CRM's flow owns matter creation, pipeline assignment, and conflict-check routing. AnyCRM doesn't drift out of date because AnyCRM never tried to own that policy in the first place.
Most competitor AI Receptionists try to maintain rules for when a matter is opened, what pipeline stage it lands on, and which source tag to apply. That approach breaks the moment your firm changes (new practice area, new intake-team workflow), and it ignores the conversion-tracking surface entirely. AnyCRM inverts the responsibility. AnyCRM stays focused on the conversation (capture, dedup, route, book, cancel) and delivers a clean lead event to the two destinations that matter: your CRM (for intake policy) and your ad platforms server-side (for conversion optimisation, attribution, and ROAS). This is a custom service baked into the AI Receptionist package. We configure the lead-receiving flow inside your CRM AND the server-side conversion tracking at onboarding, matched to your specific practice areas, ad mix, and analytics setup.
We'll be candid: as far as we can tell, none of our competitors have thought of this yet. They sell AI Receptionists as a phone-answering product. AnyCRM treats the AI Receptionist as one of two equally weighted entries into a unified lead-event pipe, and that's where the real compounding value sits — especially in legal, where one signed engagement can cover a year of Ad spend.
For your developer: how this wires into Lawmatics
The AI Receptionist asks AnyCRM for availability against the attorneys on your team and gets back open slots in the caller's timezone. No double bookings. Existing busy time on the attorney's calendar is always respected. Every AnyCRM call prevents duplicate contacts, opens or links the matter with the right practice area, sets the responsible attorney (matched from your team), writes the appointment so Lawmatics' calendar sync to Google/Outlook fires automatically, and sends the lead event straight into your CRM tagged with <code>AI Receptionist Call</code> or <code>AI Receptionist Web</code>. The same lead also feeds the AnyCRM Conversion Lift pipeline (covered in the next capability) so your Google, Facebook, and LinkedIn Ads start optimising against the call and chat leads that actually pick up the phone.
{
"invitee_timezone": "America/New_York",
"start_time": "2026-05-15",
"end_time": "2026-05-17",
"event_type_uuid": ["b050bcf6-b5b0-42a8-9359-aba11e711311"],
"multi_day": true,
"include_scheduling_url": false
}
{
"date_range_label": "Friday, May 15, 2026 – Sunday, May 17, 2026",
"event_types": [{
"event_type_uuid": "b050bcf6-b5b0-42a8-9359-aba11e711311",
"total_slots": 15,
"available_times_by_date": {
"Friday, May 15, 2026": [
{ "start_time": "2026-05-15T10:00:00-04:00", "status": "available" },
{ "start_time": "2026-05-15T10:30:00-04:00", "status": "available" },
{ "start_time": "2026-05-15T11:00:00-04:00", "status": "available" }
]
}
}]
}
{
"name": "Jane Doe",
"email": "jane@example.com",
"phone": "+14155551234",
"scheduled_datetime": "2026-05-15T11:00:00",
"invitee_timezone": "America/New_York",
"event_type_uuid": "b050bcf6-b5b0-42a8-9359-aba11e711311",
"questions_and_answers": []
}
{
"event_uuid": "a7c1f4e9-...",
"start_time": "2026-05-15T11:00:00-04:00",
"start_time_utc": "2026-05-15T15:00:00Z",
"invitee_timezone": "America/New_York",
"reschedule_url": "https://...",
"cancel_url": "https://..."
}
Turns every call and chat into a real conversion event your Google, Facebook, and LinkedIn Ads can actually optimise against. So Cost per Lead drops, ROAS goes up, and CAC stops being a guess.
If your firm runs paid Ads on Google, Facebook, or LinkedIn, here is the uncomfortable truth: those platforms only get smarter when they see real conversions. Today, a website intake form-fill counts. A real phone call from a high-intent prospective client who picked up the phone at 7pm and described their case for fifteen minutes does NOT count. So Google bids harder on the audience that fills forms (often tire-kickers comparison-shopping five firms) and ignores the audience that actually calls. Cost per Lead looks fine. CAC quietly creeps up. ROAS looks misleading. AnyCRM fixes this. Every call and chat the AI Receptionist handles is sent as a real conversion event to Google Ads, Facebook Ads, AND LinkedIn Ads. The bidding algorithm finally sees what's actually working.
Every phone call and every chat becomes a tracked conversion. Not just website form-fills.
Today, Google Ads and Facebook Ads probably think your only conversions are website intake-form submissions. That's why your Cost per Lead looks low but your intake coordinator complains the leads are weak — they're price-shoppers, not signed engagements. The high-intent traffic is calling you instead of filling a form, and the Ad platforms have no idea. AnyCRM sends every call and every chat the AI Receptionist handles into your Ad platforms as a real conversion event. Suddenly Google, Facebook, and LinkedIn can see the FULL picture of who is converting from your Ads.
Lower Cost per Lead. Better ROAS. Smaller CAC.
Once your Ad platforms can see the phone calls and chats as real conversions, they re-train on a better signal. Bidding shifts toward audiences that actually pick up the phone with a real case, not just the audience that loves filling out forms. In practice this means: Cost per Lead drops because you stop overpaying for low-intent form-fills; Return on Ad Spend goes up because the Ads now find people closer to a signed retainer; and Customer Acquisition Cost shrinks because more of your Ad budget reaches prospects who will actually convert into clients.
The same pipe carries your website forms too. One source of truth across Ads, CRM, and Analytics.
AnyCRM doesn't just track AI Receptionist conversions. It also runs your existing website intake forms and chat widgets through the same pipeline. So a lead from a Google Ad that fills your "free consultation" form AND a lead from a Facebook Ad that called the AI Receptionist three days later both end up tagged, attributed, and counted in exactly the same way. Your Ads platform stops double-counting, your analytics stop fragmenting, and your CRM stops being half-blind to where your leads actually came from.
- Cost per Lead drops. Because Google, Facebook, and LinkedIn stop wasting your Ad budget on lookalikes of low-intent form-fillers, and start finding the audience that picks up the phone.
- Return on Ad Spend (ROAS) goes up. Because the Ads now optimise toward consultations that actually convert into signed engagements, not toward whichever cheap audience generates the most form submissions.
- Customer Acquisition Cost (CAC) shrinks. Because a higher share of every Ad dollar reaches prospective clients ready to talk through their case.
- Analytics get a complete funnel. Web and voice leads sit side by side, with the same source taxonomy. You stop seeing "50% of new matters: unknown source."
- Attribution stops fragmenting. A prospective client who first clicked a Google Ad, then called the firm three days later, finally shows up correctly attributed. Today, that prospect is invisible to your Ads stack.
- You finally know if Ads are working. Most firms cannot honestly tell you whether their Google or Facebook spend is profitable. With AnyCRM's Conversion Lift, you can.
Imagine your firm spends $5,000/month on Google Ads for "family law attorney." Today, you see 80 web form-fills and assume that's the full picture. With AnyCRM running, you'll also see (say) 60 phone calls and 45 web chats the AI Receptionist handled, all flowing into Google Ads as real conversions. Suddenly Google sees 185 conversions a month instead of 80. It re-trains on that bigger, better signal. Within weeks, the bidding finds you more of the right kind of prospect — people ready to retain, not price-shoppers. Same $5,000 spend, more real consultations, lower Cost per Lead, higher signed-engagement revenue. That is what "AI Receptionist with AnyCRM" actually means for the bottom line. Not just "it answers the phone."
For your developer: how the Conversion Lift pipeline works with Lawmatics
Every contact-create and consultation-book fires through AnyCRM's Conversion Lift pipeline. The lead event lands inside your CRM for intake policy, AND fires a real conversion event server-side into Google Ads, Facebook Ads, and LinkedIn Ads using the verified origin of your registered domain. Server-side means the conversion can't be blocked by ad-blockers, doesn't degrade on iOS or Safari, and arrives with full attribution context so the Ad platforms' bidding algorithms can re-train on it. Your existing website intake forms run through the same pipeline, so Web and Voice conversions feed the SAME training signal.
Manages the full consultation lifecycle inside Lawmatics for anyone calling or chatting.
Every "push the consult to Thursday" or "actually, I want to cancel" lands with the AI Receptionist instead of on the intake coordinator's desk. AnyCRM reschedules update the existing Lawmatics appointment in place. Cancellations follow Lawmatics' own best practice. Reason recorded on the appointment, on the matter timeline. Instead of deleting the appointment and erasing the audit trail, you get crystal clarity on when a Lawmatics consultation was created, and when and why it was updated by your AI Receptionist.
Finds the consultation by email in a single step without needing a Lawmatics appointment ID
Clients DO NOT quote appointment IDs over the phone. We've tested with hundreds of callers and each time they were asked 'Can you tell me the appointment id from your email?', the response was the same: 'Why can't you find it yourself?'. AnyCRM gives the AI Receptionist an easy way to find the soonest upcoming consultation on the matter linked to the matching contact. And the AnyCRM response forces the AI Receptionist to be human. It reads back the date, time, attorney, and practice area before changing anything.
Reschedules in place and keeps the matter data clean
Rescheduling updates the existing appointment in a single confirmation. No cancel-then-rebook round-trip means the matter, the intake pipeline stage, the conflict-check status, and the calendar invite all stay intact. Failed reschedules leave the original appointment untouched.
Cancels without erasing the audit trail
When a caller cancels, AnyCRM records the cancellation the way Lawmatics' own reporting expects. Then it writes the caller's reason onto the linked matter timeline, instead of deleting the appointment and stripping WHY the consult fell through. This lets you intuitively track changes for Lawmatics consultations created or updated by your AI Receptionist.
For your developer: reschedule & cancel by email
AnyCRM's search, reschedule, and cancel all accept just an email. The soonest upcoming Lawmatics appointment on a matter linked to the matching contact is resolved inside AnyCRM. No appointment IDs at the AI Receptionist layer.
{
"email": "jane@example.com"
}
{
"meetings": [{
"event_uuid": "a7c1f4e9-...",
"event_type_name": "Haircut Only | $50",
"start_time": "2026-05-15T11:00:00-04:00",
"status": "active"
}]
}
{
"email": "jane@example.com",
"scheduled_datetime": "2026-05-16T14:00:00",
"invitee_timezone": "America/New_York",
"reason": "Customer asked to move 1 day later"
}
{
"cancelled_event_uuid": "a7c1f4e9-...",
"new_event_uuid": "f0e22c91-...",
"new_start_time": "2026-05-16T14:00:00-04:00",
"new_start_time_utc": "2026-05-16T18:00:00Z"
}
{
"email": "jane@example.com",
"reason": "Customer is unwell"
}
{
"cancelled_event_uuid": "a7c1f4e9-...",
"status": "cancelled",
"reason": "Customer is unwell"
}
Routes every caller to the right attorney. By practice area and jurisdiction. And maintains the existing attorney on an open matter instead of randomly reassigning to someone else.
Law firms run on practice areas, jurisdictions, and the attorney who actually handles each one. At setup AnyCRM imports your Lawmatics user roster into its database and enriches each attorney with practice areas, bar admissions, jurisdictions, languages, timezone, and consultation length. The AI Receptionist then routes each caller to the attorney who actually handles that matter type — and is admitted in that jurisdiction. Existing responsible-attorney assignments in Lawmatics are honoured as the source of truth.
Routes by practice area: family vs personal injury vs estate
"My spouse filed for divorce" routes to your family-law attorneys. "I was rear-ended on the 405" routes to PI. "I need to update my will" routes to estate. Each routing decision is made against the practice areas and jurisdictions you actually cover. And the existing responsible attorney on the matter is always preserved.
Honours existing matter assignments in Lawmatics
If a contact already has an open matter with a responsible attorney in Lawmatics, the AI Receptionist doesn't reassign them. The new appointment and activity note attach to the existing matter under the existing attorney. No orphaned duplicate matter, no client poached off another lawyer's docket.
Matches fresh inbound callers and website chatters to the right attorney
Net-new callers with no existing Lawmatics contact get matched to an attorney in the practice area you've designated, filtered by bar admission and jurisdiction, honouring the criteria you set in AnyCRM for matching a new intake to an attorney. The AI Receptionist doesn't fight the rules you already use.
For your developer: specialist roster & per-service routing
Team details live in AnyCRM's database, pulled once from Lawmatics at setup, enriched with practice areas, bar admissions, jurisdictions, languages, timezone, and consultation length (valuable context for the AI Receptionist that Lawmatics' user object doesn't carry by default). At runtime, one read of the team roster matches caller → practice area → attorney. New matters get assigned to the right attorney. Existing matters keep theirs. AnyCRM does NOT cache your intake pipelines, your stages, or your matter automations. That policy stays inside your CRM, where it belongs.
{}
{
"total_members": 3,
"members": [
{ "user_uuid": "3d2ed2c0-...", "name": "Michelle Arcona", "role": "user", "timezone": "America/New_York" },
{ "user_uuid": "2b00d6f3-...", "name": "Casey", "role": "user", "timezone": "America/New_York" },
{ "user_uuid": "1809c459-...", "name": "Cielona Boco", "role": "owner", "timezone": "America/New_York" }
]
}
{
"user_uuid": "3d2ed2c0-a8fc-45d7-9f67-fc3e6b898bb2"
}
{
"user_name": "Michelle Arcona",
"user_timezone": "America/New_York",
"services": [
{ "event_type_uuid": "b050bcf6-...", "name": "Haircut Only | $50", "duration": 50 },
{ "event_type_uuid": "9a858539-...", "name": "Fine Density Haircut & Finish | $70", "duration": 60 },
{ "event_type_uuid": "c1f70bb1-...", "name": "Full Head + Gloss + Finish | $335", "duration": 210 },
{ "event_type_uuid": "3c01fa3d-...", "name": "All Over Keratin Treatment | $300", "duration": 240 }
]
}
Setup in 3 steps. Battle-tested on real Lawmatics firms.
You connect Lawmatics once. AnyCRM imports your roster, your practice areas, your matter sub-types, and your intake pipeline stages. AnyCRM also wires up the receiving end inside your CRM so lead events from the AI Receptionist land where your intake automations can act on them. Then the AI Receptionist starts capturing intakes and booking consultations the same afternoon. No middleware. No prompt-engineering by you.
Connect Lawmatics (OAuth or API token, 60 seconds)
Authorize AnyCRM on your Lawmatics account via the standard OAuth grant, or paste a personal API token from your Lawmatics settings. AnyCRM scopes to the least amount of access needed for the intake + booking lifecycle. Nothing for billing, time entries, trust accounting, or document automation. You can always revoke permissions at any time from your firm-level integrations page. Every update to your Lawmatics is signed with AnyCRM's connected-app credentials so it's easy to track what the AI Receptionist did when you audit.
Import the team. Lock in your practice areas and matter types. Wire up your CRM's lead-receiving flow.
AnyCRM imports every active Lawmatics user as a bookable attorney with practice areas, bar admissions, jurisdictions, languages, timezone, and consultation length. AnyCRM also freezes the practice areas, matter sub-types, and intake pipeline stages so the AI Receptionist can only open matters that actually exist, and locks inbound-call source attribution (always AI Receptionist Call or AI Receptionist Web) so reporting stays consistent. During onboarding we set up the receiving flow inside your CRM so the lead events from the AI Receptionist land where your intake automations can act on them. AnyCRM does NOT replicate your intake pipelines, stages, or matter automations. Your CRM decides what happens after a lead is captured. AnyCRM just delivers a clean event.
Drop the AI Receptionist on your phone line and your site
Forward your business number to the AI Receptionist's number and paste the chat widget into your site. The same AI Receptionist (same team roster, same Lawmatics account, same lead-event pipe into your CRM and your ad platforms) answers both voice and web. Live the same afternoon.
Why not just use Lawmatics' intake forms + automations + scheduling links?
Lawmatics' intake forms, automations, and built-in scheduling links are excellent at the steps AFTER a prospective client has chosen to come to you via your website. They don't pick up the phone. A new caller at 9pm gets a missed call, not a contact record. A submitted intake form sits in the pipeline until the intake coordinator reads it. The scheduling link only helps people who already navigated to it. The AI Receptionist is the layer BEFORE all of that. It picks up the call, runs your intake script, books the consultation as a native Lawmatics appointment on the right attorney's calendar, writes a clean contact and matter (with the source set to AI Receptionist Call or AI Receptionist Web, intake stage, and a call summary as the first activity note), AND sends the same lead event straight into your CRM's downstream intake automations plus your ad platforms server-side. So your Lawmatics automations, your analytics, and your Google / Facebook Ads bidding all start optimising on a real conversation, not a name and a missed call.
For your developer: the enrichment layer (raw Lawmatics API vs our MCP tools)
Every tool the AI Receptionist calls is an opinionated wrapper inside AnyCRM. AnyCRM does the messy work for you. Dedup, matter creation with the right practice area, responsible-attorney assignment, intake-pipeline stage mapping, consultation-length resolution, timezone math, dual-array assembly for calendar sync, error handling, lead-event delivery into your CRM, and server-side conversion tracking into your ad platforms. All of it happens before the LLM ever sees a response. So the AI Receptionist reasons over clean, AI-aligned payloads instead of raw CRM internals.
Capturing a new intake
createOrUpdatesLawmaticsContact accepts name, email, phone, note, practice_area, jurisdiction, plus the matched attorney. AnyCRM handles dedup, picks the surviving record (or creates a new one with the right values in the right order), opens the linked matter with the right practice area and matter sub-type from the frozen setup values, drops it at the intake pipeline's first stage, locks the source, appends the intake summary as a note on the matter, sends the lead event straight into your CRM (with source AI Receptionist Call or AI Receptionist Web), AND fires a server-side conversion event into your ad platforms using the origin of your registered domain. All in one AnyCRM call.Booking the consultation
createLawmaticsContactAppointment takes email, scheduled_datetime (a naive date and time, no offset needed), invitee_timezone, and appointment_type. AnyCRM resolves the right attorney from the practice-area lane, handles the timezone and duration math, builds the host + invitee structure correctly (so Lawmatics' Google/Outlook calendar sync fires), links the appointment to the matter, sends the same lead event straight into your CRM with the booking context, fires the server-side conversion event into your ad platforms, and returns both local and UTC start times in the response.Cancelling with a reason
cancelLawmaticsAppointment takes email and reason. AnyCRM resolves the soonest upcoming consultation, records the reason on the matter timeline, and records the cancellation outcome the Lawmatics-native way. All in one AnyCRM call. No deletion, full audit trail, the consultation stays queryable in reporting and the matter pipeline reflects the real outcome.Every AnyCRM tool for Lawmatics follows the same AI-alignment contract, so the AI Receptionist never has to think about transport:
- Naive datetimes in, Lawmatics-native shape out. The AI Receptionist passes
2026-05-15T11:00:00and a timezone string. AnyCRM converts it into whatever shape the Lawmatics appointment requires, on both start and end. - Email is the identity. Cancel and reschedule never need an appointment ID at the AI Receptionist layer. Email and soonest-upcoming resolves inside AnyCRM.
- Practice area, matter type, intake stage, and source come from setup, not the LLM. The AI Receptionist can't invent a practice area or a matter type. It inherits the values you configured at setup.
- Existing responsible attorneys are sacred. If a matter already has a responsible attorney, AnyCRM preserves it. New matters only get the matched attorney when no existing matter applies.
- Matter is first-class, not an afterthought. Every booked consultation is linked to a matter, not just a contact. So the intake pipeline, conflict-check workflow, and reporting all reflect a real prospective engagement.
- Cancellation preserves the audit trail. Lawmatics' best practice for cancelled consultations is honoured so the timeline stays intact and reporting still counts the matter under the right outcome.
- Every lead event leaves AnyCRM in two places at once. Your CRM gets the lead event so your intake automations can run. Your ad platforms get the server-side conversion event so bidding optimises against real consultations. Both happen on the same AnyCRM call. No race conditions, no missing events.
- Flat, deterministic shapes. Every AnyCRM response has the same top-level keys across every tool, so the AI Receptionist's prompt never grows with edge-case branching.
- Errors are messages, not codes. An error from Lawmatics becomes a one-sentence reason the AI Receptionist can repeat to the caller without translation.
- Idempotent reschedules. If a reschedule fails mid-flight, the original Lawmatics appointment is preserved. The prospective client never ends up with nothing.
Multi-attorney setup. Team roster, practice areas & system-prompt assembly
If your firm runs more than one attorney on Lawmatics, AnyCRM imports the team roster once, you link each attorney to the practice areas and jurisdictions they actually cover, and AnyCRM bakes the result into the AI Receptionist's system prompt at setup time. Not at runtime. The AI Receptionist doesn't query your team roster on every call. It already knows who handles what.
- Team roster import. AnyCRM imports your Lawmatics users once and writes each attorney into its database keyed by
crm_user_id(with name, role, practice areas, bar admissions, jurisdictions, timezone). - Per-attorney practice areas & consultation types. For each attorney AnyCRM resolves the practice areas they actually handle and the consultation length per area. One call per person, cached.
- Practice-area visibility. Each practice area is flagged Public, Private or Ignored. The AI Receptionist only routes to and books on Public areas. You toggle this in the AnyCRM dashboard without re-deploying.
- Lead-event receiving flow inside your CRM. During onboarding we wire up the flow inside your CRM that receives lead events from AnyCRM. That's where your intake-conversion policy lives. AnyCRM doesn't try to own it.
- System-prompt assembly. The cached team roster, practice-area, and jurisdiction JSON is prepended to the AI Receptionist's system prompt before the humaniser splits (personality, etiquettes, tone, speech style). So the AI Receptionist reads the firm before it reads its own instructions.
- Runtime stays minimal. On a live call the AI Receptionist makes at most one availability call and one booking call. Never a team roster lookup. Updates to attorneys, practice areas, or consultation types re-run the cache. The AI Receptionist picks them up on its next deploy.
The end result: the AI Receptionist can match "my husband filed for divorce in Cook County last week" → family-law lane → the attorney admitted in Illinois who covers that practice area → that attorney's consultation length → that attorney's calendar availability → a booked Lawmatics appointment linked to a new matter on the right attorney's docket → a lead event delivered straight into your CRM → a server-side conversion event in your ad platforms. Without a single team roster query during the call.
Currently running for family-law, personal-injury, estate-planning, immigration, criminal-defence, and small-business boutiques. Any firm whose intake pipeline is in Lawmatics but whose phone keeps ringing after the intake coordinator has logged off.
How most AI Receptionists built on Smith.ai, My AI Front Desk, Goodcall, or Lawmatics' native AI agents fail for family-law, personal-injury, estate-planning, immigration, criminal-defence, and small-business boutiques that use Lawmatics. And why AnyCRM can't.
Most AI Receptionists fail on Lawmatics in the same handful of ways. Duplicate contacts, contacts captured without matters, invented practice areas and matter types, consultations that never sync to the attorney's real calendar, bookings outside the attorney's bar admission, deletions that destroy the audit trail, hardcoded intake-conversion rules that drift away from your real policy, and conversion data that never reaches your ad platforms server-side. AnyCRM can't fail in any of these ways, because each failure was solved one layer down inside AnyCRM. And because AnyCRM delegates intake-conversion policy to your CRM's own flow rather than trying to encode it, AND runs web and AI Receptionist conversions through a single unified conversion pipe instead of two disconnected stacks.
Duplicate contacts
Capturing a contact without a matter
Inventing practice areas, matter types, and sources that don't exist in your firm
Consultations that don't reach the attorney's real calendar
Booking outside the attorney's jurisdiction or practice area
Cancelling by deletion instead of by outcome
Encoding your intake-conversion policy in the prompt or in middleware
Web leads and AI Receptionist leads run on two separate conversion-tracking stacks
The AI Receptionist is honest because AnyCRM doesn't let it lie. And AnyCRM is sophisticated because it doesn't pretend to own policy that belongs inside your CRM, while quietly fixing the conversion-tracking gap nobody else has thought to close.
AnyCRM vs Smith.ai, My AI Front Desk, Lawmatics' native AI agents on Lawmatics
| Capability | AnyCRM | Smith.ai | My AI Front Desk | Lawmatics native AI agents |
|---|---|---|---|---|
| Live Lawmatics consultation booked DURING the call | Yes. Native Lawmatics appointment, attorney-matched, calendar-synced, linked to the matter. | Partial. Chat tier books; phone tier logs the call for the firm to book manually. | Partial. Zapier-style "Schedule Appointment" without structural detail for host-vs-invitee calendar sync. | Yes. Native to Lawmatics. |
| Opens a matter alongside the contact, every time | Yes. Atomically — contact + matter + intake stage in one call. | Conditional. Native Lawmatics integration can create matters and contacts, but on the firm's pre-shared form configuration with Smith.ai support, after the call. | No. Add Contact and Create Matter are separate Zapier-style actions. | Yes. |
| Dedup-before-write on email and phone | Yes. Always, live during the call. | Yes, but after the call ends. Native integration does search-then-update on phone or email — but the dedup state during the live AI Receptionist conversation is still stale. | No. Zapier-style "Add Contact" is one-shot. | Unclear from published materials. |
| Preserves existing responsible attorney on returning callers | Yes. Existing attorney is sacred. | Implicit, not guaranteed. | No. Can overwrite. | Unclear from published materials. |
| Routes by practice area + filters by bar admission / jurisdiction | Yes. Bar admission is part of AnyCRM's team roster. | Manual, depends on the receptionist's memory. | No. | Practice-area routing yes; bar-admission filtering not exposed. |
| Practice areas, matter types & sources frozen from your real firm values | Yes. Read at setup, baked into the prompt as a frozen table. | Not API-enforced. | No. Writes can fail on unknown enum values. | Yes (first-party data access). |
| Cancellation preserves the audit trail (outcome-recorded, not deleted) | Yes. Lawmatics-native cancellation with reason on the matter. | Reason captured as a note, not as an outcome. | No. Deletion strips the timeline. | Unclear from published materials. |
| Reschedule in place (no cancel-then-rebook) | Yes. | Manual. | No. | Yes. |
| Intake-conversion policy delegated to YOUR CRM's own flow | Yes. Lead event delivered straight into your CRM, into the receiving flow we wire up at onboarding. | No. Policy lives in the receptionist's training and the firm-supplied form configuration. | No. Hardcoded "Set Pipeline Stage" action. | Partial. Firm owns the rules and thresholds inside Lawmatics' AI agent configuration, but that surface is separate from the flow handling web-form leads. |
| Unified conversion pipe: web forms AND AI Receptionist → CRM + ad platforms server-side | Yes. Same shape, same source taxonomy, same server-side delivery to your CRM and your ad platforms. | No. Web and voice run on separate stacks. | No. Web and voice run on separate stacks. | No. Conversion tracking is not part of the product. |
| Server-side conversion events sent to Google Ads, Facebook Ads, and analytics (origin = your registered domain) | Yes. Every call and chat consultation lands server-side. | No. | No. | No. |
| Source attribution stays consistent across web and voice | Yes. AI Receptionist Call, AI Receptionist Web, plus your web form identifiers. | Manual / inconsistent. | No standardised taxonomy. | Native Lawmatics source only. |
| Scale ceiling | Bounded by Lawmatics API limits, not by staffing. | Bounded by human receptionist staffing. | Bounded by Zapier rate limits and action contracts. | Bounded by Lawmatics' AI agent capability surface and pricing tier. |
Your Lawmatics data passes through AnyCRM. It doesn't stick.
AnyCRM processes your Lawmatics data to answer the call. Then forgets it. The only thing AnyCRM persists is a conversation history ID so the AI Receptionist can recognise a returning caller. Contacts, matters, appointments, notes. All of it stays in Lawmatics, owned by your firm's account.
What AnyCRM stores
Conversation history IDs only. So the AI Receptionist can pick up where it left off if a caller hangs up and rings back. No call audio, no transcripts of contact records, no caller PII, no matter content.
What AnyCRM doesn't
Caller names, emails, phone numbers, Lawmatics contact IDs, matter IDs, your attorney roster, your practice areas, your pipeline stages, your intake-form content, your conflict-check data. None of it. AnyCRM reads what it needs, hands it to the LLM, fires the events, and discards the payload.
Where data lives
In your Lawmatics account and in whatever systems your CRM's flow forwards lead events to. Contacts, matters, appointments, notes all live in Lawmatics. Source-attributed (always AI Receptionist Call or AI Receptionist Web), attributed to AnyCRM in the audit log, revocable, and inside the firm's existing privilege-aware data boundary. AnyCRM does not build a shadow CRM alongside yours.
Revocation
Revoke the AnyCRM OAuth grant in your Lawmatics firm-level integrations page (or rotate the API token) and the AI Receptionist loses access immediately. There is no "export your data" step because there is no data to export. It was never AnyCRM's to hold.
For your developer: OAuth scopes & the smallest-surface principle
Lawmatics uses OAuth scopes (or a personal API token). AnyCRM requests only the smallest set required for the intake + booking lifecycle. Nothing for billing, time entries, trust accounting, document automation, or e-signature.
- Contacts (read + write). Read and write contacts, dedup against existing records, append notes (the intake-capture work).
- Matters (read + write). Create matters with the right practice area, sub-type, and intake-pipeline stage. Update for reschedules and cancellation outcomes.
- Appointments (read + write). Read availability and write appointments on the responsible attorney's calendar. Update to reschedule and cancel (the booking work).
- Practice areas & matter types (read). Read your firm-specific values at setup so AnyCRM only writes values that exist.
- Users (read). Read your attorney roster at setup so the AI Receptionist knows who exists and who owns existing matters.
- Not requested: billing / subscription data, time entries, trust accounting, document templates, e-signature, your other integrations.
Same OAuth grant any Lawmatics integration uses. Just a smaller surface. AnyCRM holds the access and refresh tokens (every write is signed by AnyCRM's connected-app credentials, so each contact and matter change is attributable to AnyCRM in Lawmatics' audit log). The LLM never sees the token, and every tool call is logged with the operation name, never the raw payload.
$36 to get started. No monthly subscription. No commission on voice minutes. Ever.
The AI Receptionist industry has settled into a quiet little racket: wrap a public voice provider (usually Eleven Labs) and a public chat platform in your own UI, sell it back on a monthly subscription with a metered minute allowance, and pocket a 3–5× markup on every minute your customer's caller spends on the phone. The customer never sees the underlying price. We did not want to build that business.
The Transparency Ladder — you choose how far up you climb.
Most AI Receptionist products sell one thing: a monthly plan with a minute cap. AnyCRM sells five things, ordered by how much we do for you. Start at $36 with a prompt-and-pasted DIY agent. Stop there if it's enough. Or keep climbing through the upgrades to a full custom implementation with MCP tools, conversion tracking, and a CRM-side flow we configure for you.
A prompt pack and a deployment guide. You wire up a basic AI Receptionist on web chat and voice using OUR humanizer prompts and OUR step-by-step videos.
- Two humanizer prompts (warmth, pacing, filler words)
- Web chat + voice setup videos
- Same-afternoon live deployment
- No MCP tools (no booking writes into your CRM)
- No conversion tracking
- No CRM-side lead-event flow
Add this at checkout. We walk through your setup together so the Quickstart lands faster, without you reading the docs alone.
- Live setup walkthrough
- Humanizer prompt tuning to your voice
- Q&A about your industry's quirks
Adds the first round of MCP tools so the AI Receptionist actually books appointments into your CRM (not just talks about booking them).
getAvailability+createContactAppointmentMCP tools- Live booking into your CRM
- Dedup-before-write on email and phone
- Still DIY — you wire the tools yourself with our videos
Adds search, reschedule, and cancel MCP tools. Now the AI Receptionist owns the whole appointment lifecycle — the same one we describe in the Availability and Lifecycle sections above.
- Search + reschedule + cancel MCP tools
- Audit-preserving cancellation
- Specialist / team-member routing if your CRM supports it
- Still DIY — conversion tracking and CRM flow not included
We build it for you. The whole stack: MCP tools wired, web forms unified into the same lead-event pipe, server-side conversion tracking into Google / Facebook / LinkedIn Ads, AND the lead-receiving flow inside your CRM tuned to your industry and your client configuration.
- Everything in Steps 1–3, done for you
- Unified conversion pipe (web + AI Receptionist)
- Server-side conversion tracking with your domain origin
- CRM-side lead-event flow we configure at onboarding
- One-time custom quote — no monthly subscription
How AnyCRM stacks up against the monthly-subscription crowd.
Here is what you would pay each provider to handle 500 voice minutes a month — a fair mid-volume number for a service business that picks up after hours. Sourced directly from each vendor's published pricing page.
| Cost & structure | AnyCRM | Smith.ai | My AI Front Desk | Vocaly AI |
|---|---|---|---|---|
| Pricing model | One-time fee ($36 → $850+) + you pay Eleven Labs directly | Monthly subscription, billed per call | Monthly subscription, billed per minute | Monthly subscription, billed per minute |
| Entry tier | $36 one-time | $300/mo (30 calls) | $99/mo (200 voice min) | $399/mo (2,500 min) |
| Cost for ~500 voice min / month | $0 to AnyCRM + ~$25–85 paid directly to Eleven Labs | ~$2,100/mo (Pro tier, ~300 calls) | $99 + 300 overage min @ $0.25 = $174/mo |
$399/mo (2,500 min cap) |
| Commission / markup on voice minutes | 0%. You pay Eleven Labs directly. | Bundled (per-call pricing hides minute markup) | ~3–5× markup on Eleven Labs' published rate | Bundled (rate not disclosed) |
| Hard monthly minute cap | No cap. Eleven Labs scales with your traffic. | Yes, by call count | Yes (200 min on $99 tier) | Yes (2,500 min on $399 tier) |
| Underlying voice provider disclosed | Yes — Eleven Labs. We say it openly. | N/A (human receptionists) | Not disclosed | Not disclosed |
| CRM-side lead-event flow built for you | Yes (Custom Implementation, tuned to your industry) | No | No (Zapier action list only) | No (custom tier only, opaque) |
| Server-side conversion tracking to Google / Facebook / LinkedIn Ads | Yes (Custom Implementation) | No | No | No |
| Cost over 12 months at ~500 min/mo | $36–$850 one-time + ~$300–$1,020 paid to Eleven Labs | ~$25,200 | ~$2,088 | ~$4,788 |
Pricing as listed on each vendor's published pricing page (Smith.ai, My AI Front Desk / Frontdesk, Vocaly AI, Eleven Labs) at time of publication. Eleven Labs Conversational AI is currently $0.05–$0.17/min depending on plan; "$25–85 paid directly" assumes you sit on the Free, Starter, or Creator plan for low-volume usage. Smith.ai is human-staffed; My AI Front Desk & Vocaly AI are AI-only.
One backend. Six channels. Stacked ROI.
Indicative monthly numbers based on what service businesses already see from a single channel — multiplied by the channels you switch on. Update the agent once; every channel reflects it.
Four steps. One afternoon.
No Zapier. No n8n. If you can copy and paste, you can do this.
Open the Quickstart
You get the prompt pack, the humaniser prompts, and the deployment guide.
Connect Lawmatics
One API key. The agent reads contacts and writes appointments — both ways.
Pick your channel
Web chat, voice line, or both. Same backend, same brain.
Go live
Test five calls yourself. Send the number to your team. Done.
Live by tonight. Booking customers by tomorrow.
$36 once. If it doesn't work for your business, you've lost less than dinner.