Natural-language chatbots answering taxpayer queries and guiding filing
- Who we serve
- Governments and Public Agencies
- Category
- PFM, Tax & Customs
- Value
- Experience
- Human role
- Human approves every decision
- Maturity
- B-READY topics
- Taxation
The problem
Without taxpayer virtual assistants / chatbots, revenue authorities spend their time on the routine and administrative side of the work, working through tax returns, invoices, customs declarations, third-party and financial data by hand, and the people they serve feel the delay and the inconsistency.
How it works
Taxpayer virtual assistants / chatbots - Natural-language chatbots answering taxpayer queries and guiding filing. It draws on tax returns, invoices, customs declarations, third-party and financial data and is typically owned by revenue authorities. Where the human comes in: revenue authorities review and approve before any action affects a person, a payment or a case; the AI flags, ranks and drafts. It is in production at multiple organisations; examples include ATO "Alex" (Australia, 2018, 1.4M queries/year, 88% resolution); IRAS "Ask Jamie" (Singapore, 2019); AEAT virtual assistant (Spain, 2021, 500K queries in first year).
Where the human comes in
Revenue authorities review and approve before any action affects a person, a payment or a case; the AI flags, ranks and drafts
What it needs
tax returns, invoices, customs declarations, third-party and financial data
What to plan for
Requires FAQ curation; escalation paths; multilingual capability
In the field
ATO "Alex" (Australia, 2018, 1.4M queries/year, 88% resolution); IRAS "Ask Jamie" (Singapore, 2019); AEAT virtual assistant (Spain, 2021, 500K queries in first year)
OECD Tax Administration 3.0 (2020); IMF TNM 2024/006
Public deployments by other organizations, listed for context. Not Sphere projects.