What problem does it solve?
Tax authorities face sharply seasonal demand. Around filing deadlines and after every policy change, phone lines and webchat fill with the same questions: where is my refund, how do I get a reference number, can I pay in instalments, what does this notice mean. Long waits push people to give up, file late or file wrongly, which creates more work later in compliance and correspondence.
The questions are repetitive but the stakes are not trivial: a wrong answer about a deadline or a relief can cost the taxpayer money. That is why the tax authority assistants on this page (HMRC's digital assistant and the IRS voice bots and chatbots) classify intent and return approved content, and add authenticated actions such as payment plans only behind identity checks.
How does it work?
- Recognise the intent. The assistant classifies the question (refund status, payment plan, notice, registration, how to file) on chat or on the phone.
- Answer from approved content. General questions get answers written or approved by the tax authority, with links to the guidance; unclear questions get a choice of likely meanings.
- Authenticate for account questions. For refund status, balance or a payment plan, the taxpayer verifies identity (shared secrets, PIN or national login) before the assistant reads the account.
- Act within rules. Within fixed limits the assistant can set up or change a payment plan or grant a payment extension, and confirms the result.
- Escalate. Complex, disputed or personal situations go to a human adviser, who sees the whole conversation and completes identity checks.
- Audience
- Customer facing
- Autonomy
- Supervised agent
- Adoption
- Mainstream
- Channels
- Web chat, Phone and voice, Mobile app, WhatsApp
What is it worth?
Benchmarks are computed from the public deployments below: one data point per organization per KPI, with who made each claim.
| KPI | Median | Reported range | Data points | Claimed by |
|---|---|---|---|---|
| Interactions handled | Not pooled | 500,000 to 6.5 million | 4 | 4 organization |
| Contact deflection | Too few to pool | 20% to 80% | 2 | 1 organization, 1 vendor |
| Accuracy | Too few to pool | 83% | 1 | 1 organization |
| Customer satisfaction | Too few to pool | at least 80% | 1 | 1 organization |
| Users served | Not pooled | at least 200,000 | 1 | 1 vendor |
Value drivers: Lower cost to serve, Customer experience, Compliance quality, Inclusion and access.
Indicative value
A national tax authority with 3 million assisted contacts a year
USD 1.2 million to USD 7.2 million
Human handled contact cost avoided per year
How this is calculated
Formula: contacts * routineShare * containment * costPerContact. The low scenario uses every low input, the high scenario every high input.
| Input | Low | High | Basis |
|---|---|---|---|
| Assisted phone and chat contacts per year contacts, contacts per year | 3,000,000 | 3,000,000 | The reference authority. |
| Share of contacts on routine topics (refund status, payments, forms) routineShare, fraction of contacts | 0.4 | 0.6 | Editorial assumption. Replace with your own contact reason data. |
| Share of routine contacts the assistant resolves containment, fraction of routine contacts | 0.2 | 0.4 | Editorial assumption. For context, HMRC reports that webchat escalations to advisers fell 20% while assistant interactions grew 18.8%. |
| Cost of a human handled contact costPerContact, USD per contact | 5 | 10 | Editorial assumption. Replace with your own fully loaded cost. |
What it leaves out: Gross contact cost only. It leaves out the effect on filing accuracy and late payment, the value of shorter queues at peak and the cost of building and running the assistant.
Who already uses it?
10 public deployments, strongest evidence first. Grades: A regulator or audit, B the organization itself, C vendor case study, D anonymous or estimate.
Canada Revenue Agency
Canada · Government and public sector · 2025
The Canada Revenue Agency (CRA) runs a virtual chatbot called Charlie that gives automated answers to frequently asked tax and benefit questions, alongside human staffed call centres. In an October 2025 report to Parliament, Auditor General Karen Hogan found that CRA call centre agents answered only 17 per cent of individual tax questions accurately over a four month test, and that the agency prioritized adherence to staff shift schedules over the accuracy of the information given to callers.
Hogan's report said taxpayers were more likely to get an accurate response from Charlie than from a human agent. CRA assistant commissioner Melanie Serjak told a parliamentary committee the agency would introduce more standardized training and "automation" to improve agents' accuracy. Neither the report nor the coverage of it seen for this record states Charlie's own accuracy rate, when Charlie was introduced, or how many taxpayers use it.
No outcome disclosed.
H&R Block
United States · Professional services · 2026
H&R Block launched AI Tax Assist in December 2023, a generative AI experience built on Microsoft's Azure OpenAI Service that lets DIY online and, later, desktop software customers ask open questions about tax forms, deductions, credits, tax law changes and the filing process at no extra charge, with the company's own tax professionals available if a client wants a human instead.
H&R Block says the assistant is built on content from its The Tax Institute and the experience of more than 60,000 tax professionals rather than generating unchecked answers. By March 2026 the company reported that client usage of AI Tax Assist had grown 152% since launch, with 6.45 million client messages delivered to date and 1.91 million messages that tax season alone, an 85% year on year increase, with responses delivered in an average of 2.2 seconds.
The company separately introduced Sidekick, a similar AI assistant for its own tax professionals rather than customers.
- Interactions handled: 6.5 million, cumulative since launch in December 2023, to March 2026
"Since launching in 2023, client usage of AI Tax Assist has grown 152% and delivered 6.45 million messages to date."
Claimed by: organization
Kenya Revenue Authority
Kenya · Government and public sector · 2026
The Kenya Revenue Authority (KRA) unveiled a WhatsApp based tax filing service built on an AI chatbot it calls Shuru, reachable on the authority's official WhatsApp number. Taxpayers can pull up their pre filled details, file returns, generate eTIMS invoices and obtain compliance certificates through the conversation, without logging into the iTax web portal. KRA frames the launch as part of a wider push to reach taxpayers, including small traders and individuals, outside its conventional digital filing channels.
No outcome disclosed.
HM Revenue and Customs
United Kingdom · Government and public sector · 2025
HMRC's digital assistant answers tax questions typed in plain language, matching them to intents with natural language understanding and replying with non personalised answers that link to GOV.UK guidance. It covers 60 of HMRC's more than 120 taxes, asks the user to choose between likely meanings when unsure, and needs no login. Complex questions escalate to webchat with a human adviser, who sees the whole prior conversation and only continues after identity and verification checks.
- Interactions handled: at least 5.5 million, tax year 2024/25 to 6 March 2025
"The digital assistant has had 5.48m interactions in the tax year 2024/25 (to date as at 6 March 2025)."
Claimed by: organization - Accuracy: 83%, NLU test set, March 2025, known intents
"83.03% on known intents"
Claimed by: organization - Contact deflection: 20%, webchat escalations to an adviser, tax year 2024/25 to 6 March 2025
"For webchat, 909,000 users have escalated to speak to an adviser in the tax year 2024/25 (to date as at 6 March 2025). That is a 20% decrease on the 2023/24 tax year."
Claimed by: organization
Zakat, Tax and Customs Authority (ZATCA)
Saudi Arabia · Government and public sector · 2025
Saudi Arabia's Zakat, Tax and Customs Authority launched Ask Ziyad, a generative AI assistant that answers zakat, tax and customs questions from a database of more than 130 of the authority's own guidelines, for taxpayers, importers, exporters, investors, travellers and business owners. It answers in audio or text on the ZATCA website. ZATCA positions it as part of a wider push to raise compliance and make services easier to use under Saudi Arabia's digital transformation programme.
No outcome disclosed.
Internal Revenue Service
United States · Government and public sector · 2022
Since 2021 the IRS has put intent based voice bots on many toll free lines: payment plans and balance due (with authentication so taxpayers can set up or change a payment plan), Where's My Refund and amended return status, notice clarifications, Economic Impact Payments and the Advance Child Tax Credit. On IRS.gov, chatbots answer FAQs on refunds, identity theft, payments and relief. The inventory stresses that answers are not generated: the model classifies the question and returns content approved by the business owner, or routes the call to a live assistor.
- Interactions handled: at least 3 million, calls answered by voice bots, cumulative to June 2022
"To date, the voice bots have answered over 3 million calls."
Claimed by: organization
Internal Revenue Service
United States · Government and public sector · 2020
The IRS Linguistic Policy, Tools and Services team uses a cloud machine translation application on AWS, with the IRS Publication 850 glossary of English and Spanish tax terms, to translate text and files between English and Spanish, Chinese, Korean and Vietnamese and speed up responses to taxpayers. Separately, staff use SYSTRAN neural translation, augmented with a domain dictionary and translation memories, to triage non English documents for relevance to case work and as a starting point for manual translation. Both appear in the federal AI inventory as in operation.
No outcome disclosed.
ClearTax
India · Technology and software · 2024
ClearTax, an Indian online tax filing platform, built a generative AI agent on WhatsApp, using Azure OpenAI models, for low income and blue collar workers who have tax deducted at source from their income but rarely file a return, and so miss refunds and lack the income proof lenders ask for. The agent explains taxes and filing, walks users through the filing workflow and supports nine Indian vernacular languages. It is a private filing service, not a tax authority channel.
- Users served: at least 200,000, workers who filed their returns independently
"200,000+ blue-collar workers successfully filed ITRs independently"
Claimed by: vendor - Customer savings: about INR 300 million, tax refunds claimed by users, cumulative
"300 million INR unlocked in tax refunds, improving access to credit opportunities"
Claimed by: vendor
Skatteverket
Sweden · Government and public sector · 2022
Skatteverket, the Swedish Tax Agency, launched its chatbot "Skatti" in May 2018 to answer the public's general questions about income tax returns and national registration, built on the Boost.ai conversational AI platform and trained by the agency's own staff.
A trade press interview with the agency's development strategist and AI trainer, published in 2022, reports that Skatti handles around 500,000 customer conversations a year with just over two questions per conversation, and that in a monthly sample of one in ten conversations roughly 90 percent of customers get a useful answer, such as a correct reply or a relevant link.
Customer surveys cited in the same article found that more than 80 percent of customers felt they had received a good enough answer and did not need to contact Skatteverket another way.
- Interactions handled: about 500,000, per year
"Skatti hanterar ett stort antal kundkonversationer, ungefär 500 000 om året med drygt två frågeställningar i varje konversation, men Skatteverket vill inte dra alltför stora slutsatser om vilken effekt Skatti har haft på andra kanaler in till kundservice."
Claimed by: organization - Customer satisfaction: at least 80%
"Även om Skatti inte kan svara på riktigt alla frågor är det många kunder, över 80 procent, som anser att man fått tillräckligt bra svar och att man inte behöver kontakta Skatteverket på annat sätt."
Claimed by: organization
Agencia Estatal de Administración Tributaria (AEAT)
Spain · Government and public sector · 2017
Spain's tax agency, the Agencia Tributaria, built a virtual assistant on IBM Watson Conversation so that accounting and finance professionals at large companies could ask natural language questions, around the clock, about the Immediate Supply of Information (SII), the VAT reporting regime that requires electronic invoice records within four days. It was the first time the Spanish administration used AI to support taxpayers with their tax obligations. The assistant was trained jointly by IBM and the agency's own experts on about 375 questions and answers, and by the time of the announcement it covered the whole SII process rather than only the original four topic areas.
- Contact deflection: 80%, weekly, since the July 2017 launch
"Desde su puesta en marcha el pasado mes de julio, el Departamento de Gestión de la Agencia ha visto cómo se ha reducido en un 80% el número de correos electrónicos recibidos –de 900 mensajes a 165 cada semana-."
Claimed by: vendor
How do you implement it?
A model agnostic playbook: what to prepare, the order to build in, and what goes wrong.
Data you need
- Approved answers and guidance per tax and topic, with owners and effective dates
- Contact reason data by season, to pick intents and plan for peaks
- Rules for payment plans and extensions that can be applied without judgment
Systems to integrate
- Taxpayer account, refund and payment systems through APIs
- Identity verification and step up authentication
- Telephony IVR and webchat platforms with handover to advisers
- Notice and correspondence systems, to explain letters by reference
Complexity: Medium
Information answers are low complexity; authenticated actions such as payment plans need integration with taxpayer account systems, strong identity checks and strict rules on what the assistant may change.
- 1
Start where the queues are
Use contact reason data to pick the few intents that dominate peak season (refund status, payments, notices), as the IRS did when it put voice bots on its Economic Impact Payment, notice and payment lines.
- 2
Keep answers approved
Let the model classify and retrieve, and serve content the business owner approved. The IRS inventory stresses that its bots do not generate answers.
- 3
Add authenticated self service
Add account questions and payment plans behind identity checks, with limits (amount, term) written as rules, and confirm every change back to the taxpayer.
- 4
Design escalation with context
Pass the conversation to the adviser, as HMRC's webchat advisers see the assistant history, and complete identity checks before personal discussion.
- 5
Prepare for peaks and changes
Retest before each filing season and after each budget, and plan capacity for the spike.
Guardrails
- No assessment, penalty or dispute outcome is decided by the assistant
- Account data only after identity verification, at the level the action needs
- Actions such as payment plans only within written limits, with confirmation to the taxpayer
- Answers from approved content with effective dates; refusal when the topic is out of scope
- Personal data and tax identifiers masked in logs and model prompts
KPIs to instrument
- Containment per intent, counting repeat contacts within seven days as not contained
- Escalations to advisers, before and after launch
- Intent recognition accuracy on a labelled test set
- Payment plans set up through the assistant and their default rate
- Satisfaction on assistant and adviser conversations
Human in the loop
Advisers handle escalations, disputes, hardship and anything outside the rules. Content owners approve every answer and every change after a budget; a team samples conversations weekly and reviews failed intents and complaints.
Common failure modes
- Wrong deadline or relief answers
- A fluent but wrong answer costs the taxpayer money and trust. Serve approved content, show effective dates and refuse outside scope.
- Peak season collapse
- The assistant is tested in quiet months and fails at the deadline. Load test and retest before each season.
- Authentication friction
- Taxpayers fail identity checks and fall back to the phone. Offer several proportionate methods and measure drop off.
- Private helpers without oversight
- Third party filing assistants (such as ClearTax's WhatsApp agent) help people file but are not the authority; make official guidance easy for them to use and keep the authority's own channel authoritative.
What are the risks and rules?
EU AI Act
Limited risk (transparency)
A taxpayer assistant must tell people they are interacting with an AI system (Article 50). It is not listed in Annex III as long as it only informs and applies fixed rules. It becomes high risk under Annex III point 5(a) if it evaluates eligibility for, or grants, reduces, revokes or reclaims, public assistance benefits (which can include benefits paid through the tax system). Recital 59 says systems used for administrative proceedings by tax and customs authorities are not high risk law enforcement systems; audit selection and risk scoring are covered on a separate page.
Rules that apply
Guidance
- Article 50, transparency obligations for providers and deployers of certain AI systems (European Union, Europe). Providers must design assistants so that taxpayers are informed they are interacting with an AI system, unless that is obvious from the context.
- Recital 59, AI systems used by tax and customs authorities (European Union, Europe). Systems for administrative proceedings by tax and customs authorities should not be classified as high risk law enforcement systems.
- Algorithmic Transparency Recording Standard Hub (Government Digital Service, Europe). HMRC publishes its assistant under this standard, including accuracy on known intents.
- M-25-21: Accelerating Federal Use of AI through Innovation, Governance, and Public Trust (US Office of Management and Budget, North America). Sets the rules for US federal AI use and requires agencies to inventory their AI use cases at least annually and publish the inventory, where the IRS lists its voice bots and chatbots.
Controls to put in place
- AI disclosure and a route to a human adviser on every channel
- Entry in the public AI inventory or transparency register
- Written limits for every action the assistant can take on an account
- Change control tied to the budget and filing season calendar
- Retention limits and access control on conversation logs containing tax data
Frequently asked questions
- How much volume do tax assistants handle?
HMRC's digital assistant had 5.48 million interactions in the 2024/25 tax year up to 6 March 2025, and IRS voice bots had answered over 3 million calls by June 2022, about a year after the first one went live in May 2021.
- Do tax authorities use generative AI for these answers?
Not in the deployments on this page. The IRS inventory states its chatbots and voice bots return content predetermined by content owners, and HMRC matches intents to approved answers. The IRS tested a generative AI chatbot for volunteer tax preparers as a proof of concept (listed as retired in 2025). In the private sector, ClearTax runs a WhatsApp agent on Azure OpenAI models and H&R Block's AI Tax Assist uses Microsoft's Azure OpenAI Service.
- How accurate is intent recognition?
HMRC reports 83.03% accuracy on known intents in its March 2025 test set. Plan for the rest with disambiguation questions and an easy route to a human.
How to cite this page
Blits.ai AI Use Case Library, "AI assistant for tax questions and filing support", last verified 26 September 2026, https://www.blits.ai/ai-use-cases/tax-questions-and-filing-assistant. Licensed under CC BY 4.0. Method: how we verify use cases.
Changelog
- 30 September 2026: Added deployments: Skatteverket, Agencia Estatal de Administración Tributaria (AEAT).
- 30 September 2026: Added deployments: Zakat, Tax and Customs Authority (ZATCA), Kenya Revenue Authority.
- 29 September 2026: Added deployments: H&R Block, Canada Revenue Agency.
- 27 September 2026: First published