An AI receptionist for accounting firms that answers the routine and routes the rest
We build an AI assistant for your website, phone line or shared inbox that answers routine questions from your firm's own approved answers: services, fees, how to use the portal, what to send for a return and how to book. It books discovery calls, takes messages, sorts the shared inbox and hands every tax or accounting question to a person. Projects typically cost $2,500 to $7,500 and take five to eight weeks.
The problem
What an AI receptionist for accounting firms should never do
In filing season the phones and the shared inbox fill with the same questions: have you received my documents, how do I log in to the portal, what do I need to send, when will my return be ready. Each one takes a preparer away from a return.
An assistant can help only if it is strictly limited. It must not give tax advice, must not discuss a specific client's return without verification and must hand anything technical to the right person with the context attached.
What we build
What our accounting AI chatbot includes
Approved answer library
Services, fees, portal help, document lists and office details written and approved by the firm.
Website chat, phone or inbox
The same assistant on a chat widget, a phone line or sorting the shared inbox.
Call booking
Discovery and review calls booked into the right calendar.
Inbox sorting
Emails classified as documents sent, portal help, payroll, billing or technical question, and routed.
Clear hand-off
Tax and accounting questions go to the client manager with the conversation attached.
AI disclosure and review
The assistant says it is automated, and a weekly list shows what it could not answer.
Who does what
Automation does the chasing, people make the calls.
-
01
Automated
Question arrives
A client or prospect asks by chat, phone or email.
-
02
Automated
Answer from the library
Routine questions are answered from approved wording only.
-
03
Automated
Booking or message
Calls are booked or a message is taken for the right person.
-
04
Staff review
Staff pick up
Staff answer routed messages and anything the assistant could not.
-
05
Accountant or partner decides
Tax questions
Any tax or accounting question is answered by an accountant, never by the assistant.
How it behaves
How the AI receptionist behaves
What the client sees
- A clear note that they are talking to an automated assistant
- Short answers from the firm's own wording
- A booked call or a message passed to their manager
What staff see
- Routed messages with the conversation attached
- Fewer routine calls in peak season
- A weekly list of unanswered questions
What the automation does
- Answers only from the approved library
- Refuses tax questions and hands over
- Logs every conversation
Edge cases and fallbacks
- Question not in the library
- The assistant says so and takes a message; the question goes on the review list.
- Caller wants to discuss their return
- Routed to the client manager; no details discussed.
- Suspected phishing or impersonation
- Conversation closed and flagged to the office manager.
- AI provider outage
- Chat falls back to a contact form; calls go to voicemail.
Architecture
An AI receptionist for an accounting firm at a glance.
- Input
- Logic and services
- AI step
- Data
- Output
- People
How it flows
- 1 A client asks by chat, phone or email and is told they are talking to an automated assistant.
- 2 The assistant retrieves the matching approved answer and replies only from it.
- 3 Bookings go to the calendar; messages and tax questions go to the right person with context.
- 4 Every conversation is logged and gaps in the answer library are reviewed weekly.
Project planner
How the project runs, phase by phase.
AI receptionist & client query assistant project plan
Typical time to launch: about 6 weeks, then support
-
01
Discovery
About 1 week
Collect real questions from the phones and inbox; agree what the assistant may answer.
-
02
Answer library
About 1 week
Write and approve answers, including what to say about deadlines and portal help.
-
03
Build
About 2 weeks
Channel set-up, retrieval, booking, routing, logging and admin view.
-
04
Test
1 to 2 weeks
Real, tricky and tax-advice prompts tested; staff sign off.
-
05
Launch
2 to 3 days
Soft launch out of hours or on the website first.
-
06
Support
Ongoing
Weekly review at first, then monthly library updates and seasonal wording.
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 questions collected, answers written and approved.
$500 – $1,200
-
Build
Assistant service, channels, retrieval, routing and admin view.
$1,200 – $3,800
-
Integrations
Calendar, inbox, portal help pages and alerts.
$400 – $1,200
-
Testing and evaluation set
Real, tricky and tax-advice prompts tested.
$250 – $800
-
Launch and training
Soft launch, review routine and staff walkthrough.
$150 – $500
-
Total project estimate
$2,500 – $7,500
Optional monthly care after launch is quoted with your proposal. Fixed quote after a free call. A phone line costs more to build and run than website chat. Model usage and telephony are billed to you 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; usually a small monthly amount at firm volumes.
- Telephony: Twilio at its published rates if you add a phone line or text number.
- 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 that interact with people to inform them they are interacting with an AI system, applying from 2 August 2026. We disclose everywhere.
Source: artificialintelligenceact.euUS: tax return information
Section 7216 rules limit use and disclosure of tax return information, so the assistant does not discuss a client's return and keeps return data out of the model.
Source: www.law.cornell.eduUS: Safeguards Rule vendors
AI and telephony providers that could see client information are service providers the firm must oversee under its information security program.
Source: www.law.cornell.eduFree 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 & client query assistant questions, answered.
No. Ours is built not to. It answers practical questions from your approved wording and routes every tax or accounting question to a person.
Yes. It says so at the start and offers a person at any time. In the EU this is required under the AI Act from 2 August 2026.
Only after verification and only from the portal status, if you want that. Many firms keep it to general portal help and route status questions to staff.
Yes. It classifies emails and routes them, and can draft replies to routine portal or booking questions for staff to approve.
Yes, with a voice line through Twilio. Voice costs more to build and run than chat, so many firms start with chat and the inbox.
Transcript logs and a weekly list of unanswered questions. Track conversations resolved without staff, calls booked and how quickly routed questions are picked up.
Free 20-minute call
Want this for your accountant?
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 accountants
All servicesCRM for accounting firms: pipeline to signed engagement
Every enquiry from your website, referrals, calls and partners in one CRM pipeline, with proposals, follow-ups and a hand-off into your practice system the moment an engagement is signed.
From $1,000 · About 4 weeks Details
Client onboarding, engagement letters & due diligence
Turn a signed proposal into a complete client file: engagement letter for e-signature, identity and ownership evidence, prior-accountant details and a risk summary ready for the partner.
From $1,000 · About 4 to 5 weeks Details
Tax document collection & automated chasing
Personalised request lists built from last year's file, a secure upload link, uploads matched to each item and reminders that chase on schedule until the job is ready to prepare.
From $1,000 · About 3 to 4 weeks Details