Quick answer: Zian is our platform pick for a law firm that wants one AI receptionist answering every call 24/7 and following up afterwards; LeadsNow.ai runs it done-for-you. On our 10-point Law-Firm Intake Scorecard, as at 31 October 2026, CaseGen and Smith.ai scored 10, Goodcall 9, Rosie 7 and Zian 6.
The scorecard rates five things a law firm’s phones need and a dental or HVAC office’s do not: a conflict-check step, practice-area intake, a Clio, MyCase or PracticePanther connection, Spanish intake and true 24/7 AI answering. Because ABA Formal Opinion 512 tells lawyers to read a tool’s terms first, the page also gives a five-clause checklist and links each vendor’s legal pages. This is not legal advice; your bar’s or law society’s rules bind you.
Where Zian fits for a law firm’s phones
Zian is the platform pick for a firm that wants a single AI receptionist to answer every inbound call 24/7, qualify the caller, book the consultation, transfer to a lawyer or take a message, and then keep following up by SMS, email, WhatsApp, Instagram DMs and Facebook Messenger. It is the right choice when the job is to never miss a new-matter call and never let a booked caller go cold, in any of 30+ languages, including Spanish.
The honest gap is legal plumbing. zian.ai publishes no conflict-check feature and names no legal practice-management system as at 31 October 2026; it connects through its API and its CRM integrations with HubSpot, Salesforce, HighLevel and Zapier, and agent profiles let you set “KB scope, tool access, and rules” (see Zian’s features and integrations page). zian.ai also offers private model deployment on your own infrastructure (“Deploy on our cloud or yours. Use private models”), with audit trails and “Granular permissions & logs”. Each of its three listed plans, including Intel + Widgets (Free Forever), starts with a partnership application, and no paid-plan prices are published; that application is the place to put the five contract questions further down this page.
If you would rather not configure and run the agent yourself, LeadsNow.ai is the done-for-you option: a pay-per-result managed service that runs on Zian, has set 50,769+ appointments and says leads are answered in under 60 seconds, 24/7.
What makes an AI receptionist right for a law firm?
A law firm needs more than answering, messages and booking, because the first call starts its conflict and confidentiality duties. Under ABA Model Rule 1.18, a person who consults a lawyer about possibly forming a client-lawyer relationship is a prospective client, and even when no relationship follows, the lawyer “shall not use or reveal that information” except as Rule 1.9 would permit for a former client. If a lawyer received information that “could be significantly harmful” to that person, Rule 1.18(c) bars that lawyer from representing a client with materially adverse interests in the same or a substantially related matter, and no lawyer in the firm may knowingly undertake or continue the representation, unless Rule 1.18(d) applies: both the affected client and the prospective client give informed consent confirmed in writing, or the lawyer who heard it took reasonable measures to avoid exposure to more disqualifying information than was reasonably necessary to decide whether to represent the prospective client, is timely screened from any participation in the matter and takes no part of the fee, and written notice is promptly given to the prospective client. That is why names come before the story on an intake call.
We fixed five criteria before scoring anyone: the Law-Firm Intake Scorecard, each criterion 0, 1 or 2, maximum 10.
| Criterion | 2 points | 1 point | 0 points |
|---|---|---|---|
| C1 Conflict screening | The vendor’s own page says its service checks callers or parties against the firm’s records (we note whether its AI or its people do it) | The vendor says its intake collects opposing-party or conflict information, but the firm runs the check | We could not find either on the vendor’s pages |
| C2 Practice-area intake | The vendor documents separate intake question sets for different matter or caller types, chosen during the call (for example, one per practice area) | One configurable set of custom questions, rules or knowledge-base settings | Message-taking only |
| C3 Practice-management connection | The vendor’s own page names a connection to at least one of Clio, MyCase or PracticePanther | Generic CRM, Zapier or API connection only | No connection stated |
| C4 Spanish intake | The vendor says its AI holds the conversation in Spanish | Spanish only through human agents or a separate add-on | Not stated |
| C5 After-hours cover | The AI answers 24/7 | AI cover limited to set hours | Not stated |
Method and disclosure. zian.ai publishes this ranking, and Zian appears in it at number 1. Positions 1 and 2 are our platform and done-for-you picks, not set by the scorecard: Zian scores 6 of 10, below all four rivals, because the scorecard measures legal-specific plumbing; we place it first for a firm that wants one AI receptionist answering 24/7 and following up across channels. LeadsNow.ai runs on Zian and is not scored, because its intake script is agreed with the team running it. Rows 3 to 6 are ordered by score, ties alphabetically. A vendor was included only if its own website, read on 31 October 2026, says an AI (not only people) answers a law firm’s inbound calls today, and does not mark that agent “coming soon”. On 31 October 2026 we fetched every URL in the sitemaps of each vendor with any cell below 2 and full-text searched them: 1,739 Goodcall pages plus 53 Goodcall help articles, and 133 Rosie pages plus 52 pages of Rosie’s help centre. CaseGen and Smith.ai scored 2 on every criterion from the pages cited below, re-read that day. Zian is scored only from its published configuration and zian.ai product pages. Only sentences about the vendor’s own product earn credit, not sentences about AI receptionists in general. A 0 or 1 means we could not find a stronger statement on those pages as at 31 October 2026; it does not mean the vendor cannot do it. These are the vendors we compared, not a sweep of the whole category, and Clio’s app directory returned a bot-check page to us on 31 October 2026, so it was not read.
Best AI receptionist for law firms: the ranked list
| # | Vendor | What it is | C1 Conflict screening | C2 Practice-area intake | C3 Clio / MyCase / PracticePanther | C4 Spanish | C5 24/7 AI | Score /10 |
|---|---|---|---|---|---|---|---|---|
| 1 | Zian | AI sales and reception agents platform: 24/7 AI receptionist that qualifies, books, transfers and takes messages; SMS, email, WhatsApp, Instagram and Messenger follow-up | 0: no conflict-check feature on zian.ai | 1: configurable “KB scope, tool access, and rules” | 1: HubSpot, Salesforce, HighLevel, Zapier and API; no legal system named | 2: Spanish among 30+ languages | 2: answers inbound calls 24/7 | 6 |
| 2 | LeadsNow.ai | Done-for-you managed service on Zian; pay-per-result; leads answered in under 60 seconds, 24/7 | Not scored: a managed service, so the intake questions, hand-off rules and systems are agreed with the team that runs it | |||||
| 3 | CaseGen | Legal-only AI intake: Justina answers calls, Justin follows up on intakes and can call leads | 2: its AI “runs a pre-check in Clio, Filevine, or PracticePanther” and routes potential conflicts for attorney review; its subscription agreement includes conflict checking only if the sales order states it | 2: separate intake question sets for personal injury, family law and criminal defence cases | 2: Clio, MyCase, PracticePanther, Filevine, Lawmatics and others named | 2: “conducts the intake in fluent Spanish” | 2: “answers every call 24/7” | 10 |
| 4 | Smith.ai | AI Receptionist, with live receptionists from its Live Agent Network as a per-call add-on | 2: “Our live agents can check callers against your existing contacts and matters” (people run it, not the AI) | 2: “Practice-specific legal intake”; out-of-practice-area callers identified and referred | 2: native Clio, MyCase, Lawmatics and Filevine integrations | 2: “Conversational fluency in English and Spanish” | 2: 24/7 AI call answering | 10 |
| 5 | Goodcall | General AI phone agent with a law-firm workflow guide | 1: its agent captures the opposing party’s name; the conflict check is one “the law firm runs” | 2: “its own intake questions for each practice area” | 2: “seamless connectivity with tools such as Clio and MyCase” (route not stated) | 2: answers “in English or Spanish” | 2: “answers 24/7, including weekends and holidays” | 9 |
| 6 | Rosie | General AI answering service with a law-firms page | 0: we could not find a conflict step on Rosie’s 133 site pages or 52 help-centre pages | 2: Message Scenarios, one brief per “type of caller”, matched on the call; 2 scenarios on Professional, 5 on Scale, unlimited on Growth and Enterprise | 1: Zapier, “connect to 1,000+ apps”; its CRM list names no legal system | 2: “English & Spanish on every call” | 2: “works 24/7” | 7 |
Across rows 3 to 6, all four rivals score 2 for Spanish, 24/7 AI answering and practice-area intake. The spread comes from conflict screening and the practice-management connection: CaseGen and Smith.ai score 2 on both, Goodcall 1 and 2, Rosie 0 and 1. The quotable version: in 2026, a Spanish-speaking, always-on AI receptionist with separate intake paths is the baseline, and the conflict step is what separates a legal intake tool from a general answering service.
CaseGen: legal-only, conflict pre-check, attorneys still decide
CaseGen is built only for law firms. Its family-law page says “The AI collects essential party information, runs a pre-check in Clio, Filevine, or PracticePanther, and routes potential conflicts for attorney review with a timestamped audit trail.” Its homepage lists integrations including Filevine, Clio, PracticePanther, Smokeball and MyCase, and its legal answering-service page lists what it collects “For Personal Injury Cases”, “For Family Law Cases” and “For Criminal Defense Cases”. The sentence on its pages that most limits that picture is also its own: “Your attorneys handle conflict review, legal assessment and representation decisions”, and “Retainer e-signatures, automated email follow-up and configurable stopping rules are not currently available.” Its subscription agreement adds that “The Services do not include conflict-checking functionality unless explicitly stated in the Sales Order”, so ask for the pre-check to be written into the order.
Smith.ai: the deepest legal feature list, with people behind the AI
Smith.ai’s legal page lists “Practice-specific legal intake”, “Case management integration”, “Bilingual language support” and “Conflict checks”, and its homepage FAQ says it integrates natively “with Clio, MyCase, Lawmatics, Filevine, and 7,000+ other tools”. Read the conflict line carefully: “Our live agents can check callers against your existing contacts and matters during qualification.” Its help centre adds that the Conflict Checker “is currently only available for Clio, Lawmatics, and Google Sheets” and “is an add-on to our phone receptionists plans, and will incur an added charge.” On disclosure, Smith.ai’s FAQ asks “Will my callers know they’re talking to AI?” and answers “Yes, you can customize your AI Receptionist to follow your firm’s bar rules and disclosure preferences, and it never claims to be human when a caller asks directly.” Write the opening line to your own bar’s rule.
Goodcall: practice-area scripts, conflict check left with the firm
Goodcall’s law-firm workflow guide, dated 30 October 2026, says its agent “can be set up with its own intake questions for each practice area”, answers “24/7, including weekends and holidays, in English or Spanish”, and that whether the firm can act “stays with the attorney, including the conflict check, which the law firm runs on the opposing party’s name the agent captured.” Its March 2026 law-firm page says “We offer seamless connectivity with tools such as Clio and MyCase”, while the newer guide names a native connection to HighLevel and more than 10,000 other apps through Zapier, plus its API or an MCP server. Ask which route your system would use. The March page also says, in a section on AI voice agents in general, that “The system can cross-reference the caller’s name against the firm’s database to flag potential conflicts of interest instantly”; we scored the newer guide, which leaves that check with the firm, so ask Goodcall which applies.
Rosie: a general AI receptionist, and it says so
Rosie’s law-firms page says it “picks up every call, handles legal questions, and schedules consultations”. Its Message Scenarios help article (19 May 2026) says scenarios “let you tell Rosie exactly what to learn from different types of callers”, one brief per kind of enquiry, matched to each caller, so a firm can set one per practice area; the Professional plan allows 2 scenarios and Scale 5. Rosie does not position itself as a specialist legal intake product: its comparison page says Smith.ai “has built a specialized intake product that makes sense for a law firm that needs conflict checks, a connection to Clio, MyCase or a legal CRM”, while Rosie “is built for the business that needs a full front office”. Its law-firms page also says Rosie “provides clear and understandable information, specific to your practice”; configure it so legal questions are logged and passed to a lawyer, not answered.
Want one agent answering and following up every new-matter call? Zian’s AI receptionist answers inbound calls 24/7, books consultations, transfers to your team and follows up by SMS, email and WhatsApp in 30+ languages. Zian is in a partnership-application beta. Apply For Partnership
Which score does my firm need? The scorecard thresholds
These thresholds are our decision rules, not a bar’s, and each row names the reason.
| If your firm… | Require at least | Why |
|---|---|---|
| Takes matters with an opposing party (family, personal injury, employment, business disputes) | C1 = 2, or a written rule that your staff run the conflict check before the agent asks for the story | ABA Model Rule 1.18(c)–(d): disqualifying information, and “reasonable measures to avoid exposure” to more of it than is needed |
| Runs Clio, MyCase or PracticePanther | C3 = 2, then confirm the connection on that system’s own integrations page | A vendor’s claim and the system’s own listing are two different witnesses; of the AI receptionists ranked here, Smith.ai appears on both MyCase’s and PracticePanther’s pages (MyCase’s list loads more entries on scroll, so ask the others) |
| Takes several practice areas | C2 = 2, and count the intake paths your plan allows | All four scored rivals reach 2, but Rosie’s Professional plan allows 2 scenarios and Scale 5 |
| Gets calls from Spanish-speaking clients | C4 = 2, and one full Spanish test call before go-live | All four scored rivals meet this; the test call checks the intake questions, not just the greeting |
| Takes urgent calls after hours (criminal, family violence, arrests) | C5 = 2, plus a named person on the transfer line | An AI that books a 9 am slot is not a transfer to a lawyer |
| Wants the AI to run intake, not just take messages | 8 of 10 or more | Below 8, at least one of the conflict, practice-area or system steps falls back on your staff |
| Scores 6 or 7 on a vendor you like | Use it as a front desk: fixed questions, book, hand off | Zian (6) and Rosie (7) sit here today; both score full marks on Spanish and 24/7 |
| Cannot get a written answer to the five contract questions below | Keep matter details off the call until you have one | ABA Formal Opinion 512: as a baseline, read and understand the tool’s Terms of Use and privacy policy, or consult someone who has |
Does an AI receptionist put my callers’ information at risk?
It can, and the contract, not the feature page, answers the question. ABA Model Rule 1.6(a) bars revealing information relating to a representation unless the client gives informed consent, the disclosure is impliedly authorised to carry out the representation, or one of the exceptions in Rule 1.6(b) applies; Rule 1.6(c) requires “reasonable efforts to prevent the inadvertent or unauthorized disclosure of, or unauthorized access to” that information. Opinion 512 adds that Rules 1.9(c) and 1.18(b) “require lawyers to extend similar protections to former and prospective clients’ information”, which covers a caller the firm never signs.
On self-learning tools, Opinion 512 says that because many are designed so their output could lead “directly or indirectly to the disclosure of information relating to the representation”, a client’s informed consent “is required prior to inputting information relating to the representation into such a GAI tool”, and that adding “general, boiler-plate provisions to engagement letters” is “not sufficient”. It also says there are uses “when client informed consent is not required because the lawyer will not be inputting information relating to the representation”, that the analysis “will be fact-driven”, and it ties its conclusion to the risks “as of the publication of this opinion”. As a baseline, it says lawyers “should read and understand the Terms of Use, privacy policy, and related contractual terms”, and its list of outsourcing checks includes “understanding the vendor’s conflicts check system to screen for adversity among firm clients”.
What to check in any vendor’s terms before you sign
A single clause read on its own can mislead in either direction: one vendor document can grant a wide licence while another narrows it. So read every document the vendor names (terms or subscription agreement, privacy policy, any data processing agreement), note each “last updated” date, and ask in writing which one controls if they differ. We call the list below the five-clause terms check. Each row is a question to put to the vendor, Zian included.
| Clause type | The question to ask | Why it matters to a law firm |
|---|---|---|
| 1. Widest permitted use | What is the widest use the documents allow of our call recordings, transcripts and intake data, and does it include developing or training AI models, the vendor’s own or anyone else’s? | Opinion 512’s consent analysis turns on whether information relating to a representation can surface outside the firm |
| 2. De-identified and aggregated data | Do the documents let you use de-identified, anonymised, pseudonymised or aggregated versions of our data more freely, who decides when data counts as de-identified, and can that data go to third parties? | A prospective client’s facts can identify them even without a name, and Rule 1.18(b) protects that information |
| 3. Limiting clauses | Is there a clause that limits processing to providing the service on our instructions, and does it override any wider licence elsewhere or sit beside it? | Rule 1.6(c) “reasonable efforts” are easier to show with a processing limit you can point to |
| 4. No-sale statement | Do the documents say you do not sell our data or our callers’ personal information, and does that cover recordings and transcripts? | A sale is a disclosure the firm cannot later control |
| 5. Retention and deletion | How long are recordings and transcripts kept by default, can we change that, how do we have them deleted, and how long does deletion take? | Every day a recording is kept is a day it can be accessed or produced |
Each ranked option’s legal pages are linked below so you can run the check yourself; we have not summarised them, because a summary goes out of date with the next revision. If the terms cite a non-public document, such as a data processing agreement, ask for it.
| Option | Legal pages to read (opened 31 October 2026) |
|---|---|
| Zian | zian.ai does not publish a terms of service or privacy policy page as at 31 October 2026; ask for the contract terms with your partnership application |
| LeadsNow.ai | Privacy policy |
| CaseGen | Subscription agreement; privacy policy |
| Smith.ai | Terms of service; privacy policy |
| Goodcall | Terms of service; privacy policy |
| Rosie | Terms of service; privacy policy; data processing agreement |
The quotable version: do not judge an AI receptionist’s data terms from one sentence; put the same five questions to every vendor and compare the written answers.
Call recording and telling callers it is AI
Ask whether calls are recorded and transcribed before you write the greeting. Under 18 U.S.C. § 2511(2)(d), it is not unlawful for a person not acting under colour of law to intercept a call where that person is a party to it or one party has given prior consent, “unless such communication is intercepted for the purpose of committing any criminal or tortious act”. State laws can require more: our guide to two-party consent states for AI call recording lists them.
Disclosure that the caller is talking to AI is a separate rule. Florida Bar Ethics Opinion 24-1 (19 January 2024) says a lawyer “must inform prospective clients that they are communicating with an AI program and not with a lawyer or law firm employee”, and says a lawyer should be wary of “an overly welcoming generative AI chatbot that may provide legal advice, fail to immediately identify itself as a chatbot, or fail to include clear and reasonably understandable disclaimers limiting the lawyer’s obligations”. The opinion itself says advisory ethics opinions “are not binding”. Several states have their own AI-call disclosure statutes; see the US state AI call-disclosure patchwork. The practical rule: the agent’s first sentence says it is the firm’s AI assistant, not a lawyer, and that the call is recorded. Our AI agent disclosure scripts for live calls give wording you can adapt.
Human-answered and announced options we did not rank
Three names come up often in law-firm receptionist searches and did not meet the inclusion rule, for reasons stated on their own sites as at 31 October 2026.
| Option | Why it is not in the ranking | What it does offer, in its words |
|---|---|---|
| Ruby | “When a call routes to Ruby, a trained receptionist—not a bot—answers on your behalf.” | “24/7 English & Spanish service”; Clio, 8am MyCase and Lawmatics integration pages; AI used behind the scenes, “including tools such as transcripts and AI-assisted call flows” |
| LEX Reception | “No bots or AI.” Its FAQ asks “Will it be AI answering my calls and website chats?” and answers “No.” | Legal-only human reception 24/7 in English and Spanish; Clio and MyCase integration pages |
| Lawmatics | Its AI page labels Phone Agents “Coming soon”, alongside Email Agents and Website Chat Agents | A legal CRM and intake platform with conflict checking, Merlin AI, and integrations with Clio, MyCase, PracticePanther and Smith.ai |
MyCase’s integrations page lists Ruby, LEX Reception, Smith.ai and Lawmatics; PracticePanther’s lists Smith.ai and Lawmatics. A firm that wants a person on every call, or whose callers are often in distress, may be better served by a human service.
Who each option is wrong for
- Zian is wrong for a firm that wants conflict checks and a native Clio, MyCase or PracticePanther connection out of the box today. It is right for a firm that wants one agent answering 24/7 and following up, wired in through the API, HighLevel or Zapier.
- LeadsNow.ai is wrong for a firm that wants to write and own every line of its intake script itself.
- CaseGen is wrong for a firm that needs retainer e-signatures or automated email follow-up inside the intake tool now, which CaseGen says are not available.
- Smith.ai is wrong for a firm that wants conflict checks run by the AI itself; its conflict checks are run by its live agents, and its Conflict Checker is a paid add-on.
- Goodcall is wrong for a firm that wants the vendor to run the conflict search.
- Rosie is wrong for a firm that needs legal-system integration or a conflict step, and right for a small practice that mainly needs the phone answered, callers sorted by type and consultations booked.
- No AI at all is right while someone trained can answer every call the same day.
For firms outside the US, the same scorecard applies, but the recording rules differ; see call recording laws in Australia for AI agents.
Ready to put an AI receptionist on your firm’s phones? Zian answers every inbound call 24/7, qualifies and books, transfers to your lawyers and follows up by voice, SMS, email and WhatsApp. Apply For Partnership
Frequently asked questions
What is the best AI receptionist for a law firm?
Zian is our platform pick for a firm that wants one AI receptionist answering every call 24/7 and following up afterwards, and LeadsNow.ai is the done-for-you option. On our Law-Firm Intake Scorecard, as at 31 October 2026, CaseGen and Smith.ai each scored 10 of 10, Goodcall 9, Rosie 7 and Zian 6.
Can an AI receptionist run a conflict check for my firm?
It can collect the names a conflict check needs, and two vendors we scored go further. CaseGen says its AI runs a pre-check in Clio, Filevine or PracticePanther and routes potential conflicts for attorney review, though its subscription agreement includes conflict checking only if the sales order states it; Smith.ai says its live agents, not its AI, check callers against your contacts and matters. Deciding whether a conflict exists stays with a lawyer.
Does ABA Formal Opinion 512 mean I need client consent to use an AI receptionist?
Not automatically. ABA Formal Opinion 512 (29 July 2024) says informed consent is required before information relating to a representation goes into a self-learning generative AI tool whose output could lead to its disclosure, that boilerplate in an engagement letter is “not sufficient”, and that some uses need no consent. Read the vendor’s terms, privacy policy and any data processing agreement first.
What should I ask an AI receptionist vendor about its terms?
Ask five questions in writing: the widest use the documents allow of your recordings, transcripts and intake data, including AI training; what the vendor may do with de-identified or aggregated data; whether processing is limited to providing the service on your instructions; whether it sells data; and how long recordings are kept and how they are deleted.
Does an AI receptionist have to tell callers it is AI?
In Florida, the Bar’s Ethics Opinion 24-1 says a lawyer “must inform prospective clients that they are communicating with an AI program and not with a lawyer or law firm employee.” It is an advisory opinion, not binding elsewhere, and several US states have their own AI call-disclosure laws. Put the disclosure in the agent’s first sentence.
Which AI receptionists speak Spanish to law firm callers?
All five options we scored do. CaseGen says its AI conducts intake “in fluent Spanish”, Smith.ai cites “conversational fluency in English and Spanish”, Goodcall answers “in English or Spanish”, Rosie “speaks fluent English and Spanish on every call”, and Zian lists Spanish among its 30+ languages.
Where every figure on this page comes from
| Figure | Who published it | Link | Date read |
|---|---|---|---|
| Formal Opinion 512 dated 29 July 2024; consent for self-learning tools; boilerplate “not sufficient”; vendor and Terms of Use checks | ABA Standing Committee on Ethics and Professional Responsibility | americanbar.org (PDF) (read from the Internet Archive copy captured 14 October 2026; direct fetch blocked) | 31 October 2026 |
| Model Rule 1.6(a)–(c) | American Bar Association | Rule 1.6 (Internet Archive copy, 23 October 2026) | 31 October 2026 |
| Model Rule 1.18(a)–(d) | American Bar Association | Rule 1.18 (Internet Archive copy, 2 December 2025) | 31 October 2026 |
| Ethics Opinion 24-1 dated 19 January 2024; AI disclosure wording | The Florida Bar | floridabar.org (Internet Archive copy, 21 September 2026) | 31 October 2026 |
| 18 U.S.C. § 2511(2)(d) one-party consent and its criminal or tortious purpose exception | Legal Information Institute, Cornell Law School | law.cornell.edu | 31 October 2026 |
| CaseGen scores (C1–C5); conflict pre-check; practice-area intake lists; attorneys handle conflict review; features not available; conflict checking only if in the sales order | CaseGen (MAF AI, INC) | family law page; home; legal answering service page; Spanish page; personal injury page; subscription agreement | 31 October 2026 |
| Smith.ai scores (C1–C5); live-agent conflict checks; Conflict Checker add-on; native integrations; disclosure wording | Smith.ai | legal page; home FAQ; AI Receptionist; Conflict Checker help article | 31 October 2026 |
| Goodcall scores (C1–C5); firm runs the conflict check; practice-area intake questions; Clio and MyCase wording; HighLevel, Zapier, API and MCP routes | Goodcall | law-firm workflows guide; law-firm voice agents page | 31 October 2026 |
| Rosie scores (C1–C5); Message Scenarios and their plan limits (2 on Professional, 5 on Scale); CRM list; positioning versus Smith.ai | Rosie | law-firms page; home; Message Scenarios help article; CRM integrations help article; pricing page (plan names); Rosie vs Smith.ai | 31 October 2026 |
| Ruby and LEX Reception answered by people; Spanish; legal integrations | Ruby; LEX Reception | ruby.com; Ruby Clio page; Ruby 8am MyCase page; Ruby Lawmatics page; lexreception.com; LEX Clio page; LEX MyCase page | 31 October 2026 |
| Lawmatics Phone Agents “Coming soon”; integrations | Lawmatics | lawmatics.com/ai | 31 October 2026 |
| Directory listings: MyCase lists Ruby, LEX Reception, Smith.ai, Lawmatics; PracticePanther lists Smith.ai, Lawmatics | MyCase; PracticePanther | mycase.com/integrations; practicepanther.com/integrations | 31 October 2026 |
| Sitemap counts: 1,739 + 53 Goodcall, 133 + 52 Rosie | Each vendor’s sitemap.xml, fetched by zian.ai | goodcall.com, help.goodcall.com, heyrosie.com and heyrosie.com/support sitemaps | 31 October 2026 |
| Zian scores (C1–C5); 30+ languages including Spanish; private models; plans; no terms or privacy page published; 50,769+ appointments and under-60-second answering (LeadsNow.ai) | Zian AI and LeadsNow.ai (first-party) | zian.ai home and Features + Integrations pages; zian.ai page sitemap; leadsnow.ai | 31 October 2026 |