An AI receptionist for law firms that captures intake and never gives legal advice
We build an AI assistant for your website and phone line that answers practical questions from your firm's approved wording, such as practice areas, fees, office details and how consultations work, captures intake details for the conflict check, books consultations and routes urgent matters to the on-call lawyer. It says it is automated and never gives legal advice. Projects typically cost $2,500 to $7,500 and take five to eight weeks.
The problem
What an AI receptionist for lawyers must never do
People look for a lawyer when something has gone wrong, often in the evening or at the weekend. If they reach voicemail or a contact form with no reply, many call the next firm. Staffing reception around the clock is expensive for most firms.
An assistant can fill the gap only if it is tightly bounded. It must not give legal advice, must not suggest the firm will take a case before the conflict check, must protect what the caller shares and must put genuinely urgent matters in front of a lawyer quickly.
What we build
What our law firm AI chatbot includes
Approved answer library
Practice areas, fees and funding options, office details and the consultation process, written and approved by the firm.
Phone and website chat
The same assistant answering calls and website chat, with a person available on request.
Intake capture
Collects contact details, matter type and every name for the conflict check, and files it to the CRM.
Consultation booking
Books into the right lawyer's calendar once intake is complete.
Urgent routing
Arrests, injunctions, imminent hearings and similar urgent matters go to the on-call lawyer.
Disclosure and review
Clear AI disclosure and a weekly review of transcripts and unanswered questions.
Who does what
Automation does the chasing, people make the calls.
-
01
Automated
Call or chat
A prospect or client contacts the firm by phone or website.
-
02
Automated
Answer or intake
Practical questions are answered from the library; new matters go through intake.
-
03
Automated
Book or route
Consultations are booked and urgent matters are routed to the on-call lawyer.
-
04
Staff review
Intake team follows up
Staff review transcripts, complete intake and handle messages.
-
05
Attorney or solicitor decides
Legal questions
Every legal question and the decision to take a matter stays with a lawyer.
How it behaves
How the AI receptionist behaves
What the caller sees
- A clear note that they are talking to an automated assistant
- Practical answers and a structured intake
- A booked consultation or an urgent call back from a lawyer
What staff see
- Complete intakes in the CRM ready for the conflict check
- Urgent matters routed to the on-call lawyer
- A weekly list of unanswered questions
What the automation does
- Answers only from approved wording
- Refuses legal questions and hands over
- Logs every conversation with restricted access
Edge cases and fallbacks
- Caller is the opposing party on a current matter
- Intake is taken without discussing any matter and flagged for the conflict process.
- Caller is distressed or at risk
- The assistant gives the firm's approved emergency wording and routes to a person at once.
- Question outside the library
- The assistant says it cannot answer and takes a message.
- AI or telephony outage
- Calls fall back to voicemail and chat to a contact form, with an alert to the office manager.
Architecture
An AI receptionist for a law firm at a glance.
- Input
- Logic and services
- AI step
- Data
- Output
- People
How it flows
- 1 A caller or website visitor is told they are speaking with an automated assistant.
- 2 Practical questions are answered from approved wording; new matters go through structured intake.
- 3 Intake goes to the CRM and a consultation is booked; urgent matters go to the on-call lawyer.
- 4 Every conversation is logged and reviewed weekly.
Project planner
How the project runs, phase by phase.
AI receptionist & law firm chatbot project plan
Typical time to launch: about 6 weeks, then support
-
01
Discovery
About 1 week
Real calls and chats, practice areas, urgent matter types and on-call arrangements.
-
02
Answer library
About 1 week
Answers and intake scripts written and approved, including what the assistant must refuse.
-
03
Build
About 2 weeks
Voice and chat channels, retrieval, intake, booking, routing and logs.
-
04
Test
1 to 2 weeks
Real, tricky and legal-advice prompts tested; lawyers sign off.
-
05
Launch
2 to 3 days
Out-of-hours first, then wider.
-
06
Support
Ongoing
Weekly transcript review at first, then monthly updates.
What it runs on
Real products only, connected through the access each vendor provides. See all integrations
Cost estimate
What it costs, line by line.
-
Discovery and answer library
Real calls collected, answers and intake scripts approved.
$500 – $1,300
-
Build
Voice and chat, retrieval, intake, booking and routing.
$1,200 – $3,700
-
Integrations
CRM, calendars, telephony and alerts.
$400 – $1,200
-
Testing and evaluation set
Real, tricky and legal-advice prompts tested.
$250 – $900
-
Launch and training
Soft launch, review routine and team walkthrough.
$150 – $400
-
Total project estimate
$2,500 – $7,500
Optional monthly care after launch is quoted with your proposal. Fixed quote after a free call. Voice costs more to build and run than chat. Model usage and telephony are billed to your accounts directly.
Monthly running costs you pay directly
Estimates from the vendors' published pricing, checked November 2026. Billed to you by each vendor, never marked up.
- AI model usage: Billed by the provider per use; voice calls use more than chat.
- Telephony: Twilio Voice and SMS at their published rates.
- Hosting: n8n Cloud from about €20 a month, or your own server.
What pushes cost up
- Systems without an API, or with integration access that must be requested from the vendor
- Writing data back into your core system rather than only reading from it
- Several locations, brands or very different processes to support
- Custom apps, dashboards or a voice line on top of the workflows
What keeps cost down
- One location and one clear process to start with
- Cloud software with a documented API
- Using tools you already pay for instead of adding new ones
- Approved wording and sample data ready at the start
Privacy and consent
Rules we design for, with the sources.
EU: tell people they are talking to AI
Article 50 of the EU AI Act requires AI systems interacting with people to inform them they are interacting with AI, from 2 August 2026. We disclose everywhere.
Source: artificialintelligenceact.euUS: prospective client confidentiality
Model Rule 1.18 protects information shared by prospective clients, so transcripts are access-restricted and the assistant asks only what intake needs.
Source: www.americanbar.orgUS: AI tools and client information
ABA Formal Opinion 512 covers confidentiality and competence when lawyers use generative AI; we document what the vendor does with data so the firm can assess it.
Source: www.americanbar.orgEU and UK: processor contracts
AI and telephony vendors processing personal data need an Article 28 GDPR contract.
Source: gdpr-info.euFree tools
Try these first, free.
How we deliver
Agile delivery, in 1 to 2 week sprints.
Every sprint
- 1 Sprint planning. At the start of each sprint we agree which backlog items we will finish, each with written acceptance criteria you can check.
- 2 Daily stand-up. A short internal check-in on progress and blockers. You get a written update in your Slack or Teams channel, not another meeting.
- 3 Sprint review and demo. At the end of each sprint we demo what was built on test data or in a shadow run, and you accept it or ask for changes.
- 4 Retrospective. The team looks at what went well and what to change in the next sprint, and we share anything that affects you.
How scope stays under control
- Product backlog
- Every feature, fix and question in one prioritised list you can see at any time.
- Acceptance criteria
- Plain-language conditions for "done" on each item, agreed before work starts.
- Change requests
- New ideas go into the backlog with an estimate. Nothing changes scope or price without your written approval.
- User acceptance testing (UAT)
- Before launch your team tests the real workflow against the acceptance criteria and signs off.
Tools we use
Project manager / Scrum master
Runs the sprints, keeps the backlog and timeline honest, and is your single point of contact.
Business analyst
Maps how the work runs today, writes the workflow specification and acceptance criteria with your team.
Automation engineer
Builds the n8n workflows, integrations, AI steps and error handling.
Backend developer
Writes custom code where a no-code step is not enough: APIs, data sync, secure storage.
Frontend / mobile developer
Builds forms, booking pages, dashboards, web apps or Android apps when the project needs them.
QA engineer
Tests every workflow against the acceptance criteria, including edge cases and failure paths.
DevOps engineer
Sets up hosting, access, backups, monitoring and alerts, and the deployment pipeline.
Who does what at each phase
- Free call
- Project manager, business analyst
- Understand the problem, check it is worth automating and outline a rough range.
- Discovery
- Business analyst, automation engineer
- Map the current process, systems and data, and agree success measures.
- Design
- Business analyst, automation engineer, backend developer
- Write the workflow specification, data flows, compliance notes and backlog with acceptance criteria.
- Sprints
- Automation engineer, developers, QA
- Build, test and demo in 1 to 2 week sprints; you accept or adjust after each demo.
- UAT and launch
- QA, DevOps, project manager
- Your team tests and signs off, we switch on, monitor closely and train the team.
- Support
- Automation engineer, DevOps
- Stabilisation window, then optional monthly care with monitoring and changes.
A point of contact
One person who can answer questions and approve decisions, with about an hour a week during the project.
Access
Admin or API access to the systems involved, created as separate accounts with the least access needed.
Sample data
Real but non-sensitive records (or de-identified ones) so we can design and test against reality.
Approved wording
Message templates, policies and consent wording (for SMS, your opt-in and opt-out text) reviewed by you.
Vendor agreements
Signed agreements with the software vendors that will handle personal data, such as a BAA or processor contract.
Time for testing
A few hours from the people who will use the system, for the demos and user acceptance testing.
Working system
Workflows, integrations and any apps running in your accounts, under your keys.
Documentation
Workflow specification, data-flow map, run book and exported workflow files.
Training
A walkthrough for the team and a short recorded video for new starters.
Handover
All access, credentials and code handed over; you can keep us or take it in-house.
Stabilisation window
Fixes for anything that does not meet the agreed acceptance criteria after launch.
Support options after launch
No plan
You run it yourselves after the stabilisation window and contact us when you need a change.
Monthly care
Monitoring, error alerts, small changes and updates each month, with an agreed response time.
Priority care
Faster response times for business-critical workflows and a monthly review call.
How a project moves through our team
- Input
- Logic and services
- People
- Output
- Data
How it flows
- 1 A free call with the project manager and business analyst to understand the problem and whether it is worth building.
- 2 Discovery and design produce a written specification, data-flow map and a backlog with acceptance criteria.
- 3 The team builds in 1 to 2 week sprints; you review a demo at the end of each and accept or adjust.
- 4 Your team runs user acceptance testing, we launch, then monitor and improve under a support plan.
FAQ
AI receptionist & law firm chatbot questions, answered.
One that stays inside approved wording, captures intake that is good enough for a conflict check, routes urgent matters reliably and connects to your CRM and calendars. We build to those requirements around your own systems rather than a one-size product.
No. Ours refuses legal questions, explains that a lawyer will respond, and never suggests the firm will take a matter before the conflict check.
Yes. It says it is automated at the start and offers a person. In the EU this is required from 2 August 2026.
Urgent categories you define, such as an arrest or an imminent hearing, are routed to the on-call lawyer by call or text, with the intake attached.
We use vendors whose data terms the firm has reviewed, restrict transcript access, collect only what intake needs and give you a written data-flow summary.
Track out-of-hours enquiries captured, consultations booked, urgent routes answered and questions it could not handle.
Free 20-minute call
Want this for your law firm?
Book a free 20-minute call. We will look at how the work runs today, tell you honestly whether it is worth building and give you a fixed quote if it is.
More for law firms
All servicesLegal CRM & enquiry follow-up automation
Every enquiry from your website, directories, referrals and phones in one legal CRM pipeline, with fast acknowledgements, consultation booking and follow-ups until the prospect retains you or declines.
From $1,000 · About 4 weeks Details
Client intake & conflict check preparation
Structured intake by practice area that collects every party, company and related name a conflict search needs, runs the search in your practice system and puts the results in front of a lawyer.
From $1,000 · About 4 to 5 weeks Details
Legal document automation & matter filing
Engagement letters and routine documents drafted from your approved templates and matter data, plus incoming email, scans and e-filing notices filed and named to the right matter.
From $1,000 · About 4 to 5 weeks Details