What is this course about?
Firms lose prospective clients to unanswered calls, and the first conversation carries ethical duties before anyone is retained. This course designs an AI receptionist around those duties: what it may and may not say, limiting what a prospective client discloses, conflicts checks mid-call, disclosure that the caller is speaking with AI, outbound calling rules, supervision and escalation.
Who is this course for?
- Managing partners of small and mid-sized firms
- Intake managers and client services staff
- Firm administrators and operations leaders
- Legal technology staff
What do I need before starting?
- Your firm's current intake script or process
- Recommended: Client Intake and Conflicts Checking with AI (LEG-5)
What will I be able to do afterwards?
- Define what an AI receptionist may do and must never do
- Design intake that limits prospective-client disclosure until conflicts clear
- Specify disclosure and escalation behavior
- Identify the outbound calling rules counsel must review
- Set up supervision of the receptionist under the firm's ethics obligations
What does each module cover?
What should an AI receptionist do, and what must it never do?
35 minAnswer, route, collect and schedule; never advise, promise outcomes or quote fees it has not been given.
Objectives
- List permitted and prohibited behaviors
- Write refusals that still help the caller
- Define the hand-off to a person
Topics
Activity. Write the receptionist's permitted and prohibited behavior list.
What does Rule 1.18 mean for the first conversation?
40 minDuties to prospective clients begin before engagement, so intake collects only what is needed to check conflicts.
Objectives
- Summarize duties to prospective clients
- Limit disclosure during intake
- Record what was disclosed
Topics
Activity. Rewrite your intake script to collect only what conflicts checking needs.
How does the receptionist run a conflicts check mid-call?
40 minParty names and adverse parties checked before the caller describes the matter.
Objectives
- Collect party and adverse party names first
- Query the conflicts system
- Hold the conversation when a potential conflict appears
Topics
Activity. Design the mid-call conflicts step and its three outcomes.
How do you tell callers they are speaking with AI?
35 minDisclosure at the start of the call and on request, with requirements that vary by jurisdiction.
Objectives
- Write the disclosure
- Handle callers who ask for a person
- List jurisdiction questions for counsel
Topics
Activity. Write the opening disclosure and the transfer path.
What do the TCPA and solicitation rules mean for outbound calls?
40 minThe FCC ruled in 2024 that AI-generated voices are artificial under the TCPA, so outbound AI calls need counsel's review.
Objectives
- Separate inbound answering from outbound calling
- List the TCPA questions for counsel
- Apply the Model Rules on solicitation
Topics
Activity. Classify every call the receptionist would place and flag those for counsel.
How do you supervise an AI receptionist?
35 minSupervision duties applied to an AI tool, with transcript review and correction.
Objectives
- Assign a supervising lawyer
- Review transcripts on a schedule
- Correct and retrain from errors
Topics
Activity. Write the supervision schedule and review checklist.
How do you handle urgent, distressed and after-hours callers?
35 minEscalation for emergencies, imminent deadlines and distress, at any hour.
Objectives
- Define urgent triggers
- Escalate to an on-call person
- Flag possible deadlines for a lawyer
Topics
Activity. Write escalation rules for five urgent scenarios.
Building the receptionist call flow
40 minThe workshop: a complete call flow tested with role-played calls.
Objectives
- Assemble the call flow
- Test it with role-played calls
- Revise from the failures
Topics
Activity. Test the call flow on ten role-played calls and fix every failure.
What is the capstone project?
AI receptionist call flow and supervision plan
Design an AI receptionist for your firm: permitted behaviors, limited-disclosure intake, the conflicts step, AI disclosure, escalation, outbound-call review and supervision.
Deliverable: A call flow, a supervision plan and the list of questions referred to the firm's ethics counsel.
How are learners assessed?
- Call flow tested against role-played calls that attempt to elicit legal advice
- Intake script reviewed for disclosure beyond what conflicts checking needs
- Supervision plan reviewed by a supervising lawyer
What ships with the course?
Facilitator guide
Session-by-session running order, discussion prompts, and the questions that reliably derail a room.
Learner workbook
Exercises, checklists, and the templates each module's activity produces.
Hands-on lab environment
A sandboxed ibl.ai deployment so exercises run against real agents, not screenshots.
Assessment bank
Scenario questions and rubric criteria mapped to each stated learning outcome.
Source bibliography
Every primary regulation and standard cited on this page, linked and dated.
Which AI agents does this course use?
The hands-on modules run against agents already deployable on the ibl.ai platform for legal.
Where does the course material come from?
Every module is grounded in primary sources — the regulation, standard, or research itself, not a summary of it. Each was resolved at authoring time.
- Model Rules of Professional Conduct
American Bar Association
Rules 1.18, 5.3 and 7.3, which frame intake, supervision and solicitation.
- Formal Opinion 512: Generative Artificial Intelligence Tools
American Bar Association
The ABA's July 2024 opinion on lawyers' duties when using generative AI tools.
- FCC Makes AI-Generated Voices in Robocalls Illegal
Federal Communications Commission
The 2024 declaratory ruling that AI-generated voices are artificial under the TCPA.
- 47 U.S. Code § 227: Restrictions on use of telephone equipment
Cornell Legal Information Institute
The TCPA statute text.
- AI Risk Management Framework
NIST
The govern, map, measure and manage functions used to structure risk review.
Delivery notes
Binding guidance for anyone preparing and delivering this course.
- The course teaches design and evaluation. Every ethics and TCPA question is for the firm's ethics counsel, and state rules differ from the Model Rules.
- Module 2 is the module firms most often get wrong: a friendly receptionist invites callers to tell their whole story before conflicts clear.
- Use role-played calls only. Never test with real prospective clients.
- Coordinate with LEG-5, which covers conflicts checking in depth.
Why run AI training on a platform you own?
You own the course, not a licence to it
Course content, learner data, and the platform run inside your perimeter — you own all the code and the data.
Model-agnostic delivery
Run the course's AI components on any LLM — Claude, GPT, Llama, Gemini, Command — and switch anytime.
No per-seat training licences
Usage-based or self-hosted, so cost tracks actual use rather than headcount.
Deploy anywhere
Cloud, private VPC, on-premise, or fully air-gapped — including for cohorts that cannot use public AI tools.
Frequently asked questions
What does the AI Receptionists for Law Firms: Intake and Ethics course cover?
Firms lose prospective clients to unanswered calls, and the first conversation carries ethical duties before anyone is retained. This course designs an AI receptionist around those duties: what it may and may not say, limiting what a prospective client discloses, conflicts checks mid-call, disclosure that the caller is speaking with AI, outbound calling rules, supervision and escalation. It runs 5 hours across 8 modules, at foundational level, and closes with a capstone: AI receptionist call flow and supervision plan.
Who should take AI Receptionists for Law Firms: Intake and Ethics?
It is written for Managing partners of small and mid-sized firms, Intake managers and client services staff, Firm administrators and operations leaders, Legal technology staff. Prerequisites: Your firm's current intake script or process; Recommended: Client Intake and Conflicts Checking with AI (LEG-5).
Can we run this course on our own infrastructure?
Yes. ibl.ai is model-agnostic and deploy-anywhere — cloud, private VPC, on-premise, or fully air-gapped — and you own all the code and the data. Cohort data, submissions, and any material learners upload stay inside your perimeter, which matters for legal teams that cannot send work to a public AI tool.
How do we get access to AI Receptionists for Law Firms: Intake and Ethics?
Request access and we will set it up for your cohort — hosted by ibl.ai, or running against your own deployment. Tell us the group size and timing you need, and whether it should run inside your own perimeter.
How much does AI training for legal cost on ibl.ai?
There is no per-seat pricing — you pay for usage or self-host and pay only for the infrastructure, so a 5,000-person rollout does not cost 5,000 licences. 1.6M+ users across 400+ organizations run the platform this way, including NVIDIA, MIT, and Syracuse University.