How AI products answer tax research questions and support indirect tax and provision work, the professional review they need, and questions for a vendor.
- Products listed
- 5
- Makers in the SEC ticker file
- 2
- Filing excerpts
- 1
- Notes
- 17
Lead schedule.Data the makers in this workpaper name
One stroke per record, in fives. Systems named by 4 or more records; every system is in Appendix C.
The schedule scrolls sideways; the workpaper column stays in place.
| W/P | Banks | NetSuite | ERP | SAP | Cards | Intacct | Workday | Claude | CRM | QuickBooks | Dynamics | Oracle | Payments | Payroll | Salesforce | No data named |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 9Tax research | 4 |
Answer sheet.What the makers' pages in this workpaper answer
One stroke per record: solid where the maker's own page answers the question, dotted where the pages read are silent. A count of what the pages say, not a score.
| W/P | Data it names | Where a person reviews | Model or data handling |
|---|---|---|---|
| 9Tax research | 1 of 5 | 2 of 5 | 2 of 5 |
1The work
AI products for tax do two different things: they answer research questions in plain language with citations to authority, and they automate parts of compliance such as tax determination, classification, e-invoicing and filing. In both, a qualified person remains responsible for the position taken. The makers in this note describe a generative research tool that cites its sources, AI agents inside an indirect tax platform, and AI across a finance and tax platform.
Tax research means finding and reading the authority (statute, regulations, rulings, cases, commentary) that answers a specific question for specific facts, and documenting the reasoning. Provision work (computing current and deferred tax for the financial statements) and compliance work (returns, indirect tax, e-invoicing mandates) are rules-heavy and data-heavy, with deadlines and penalties.
Language models are good at finding and summarising text and poor at knowing when they are wrong. A tax answer that cites the wrong section or misses a later ruling can look as confident as a right one. That is why the research products in this note stress citations, and why indirect tax products describe keeping deterministic calculation separate from AI.
A person must stay in the loop for the facts, the conclusion and the sign-off. In the United States, Treasury Department Circular 230 sets the rules of practice before the IRS; the IRS says it "governs practice before the IRS by setting forth mandatory rules of conduct for tax professionals."1 Using a tool does not move that responsibility.
2Where AI is applied
Makers describe plain-language research answers with citations to authoritative content, the option to combine a user's own documents with the research database, AI agents for classification and compliance workflows, and in-app guidance with human review where judgment is needed.
Exhibit 9.1.What the makers say, in their words, alphabetical by maker
- Avalara, Avalara AI compliance
AI agents monitor data and behavior, provide compliance insights and risk guidance, and automate key tax tasks including calculations, filings, and classifications.
q8 - Blue J, Blue J tax research
The Blue J platform is a cloud native generative AI for tax research application that answers challenging tax law questions using a natural language interface.
q10 - Lucanet, Intelligence Core, Lucanet Lume
The intelligence built in to the CFO Solution Platform is designed to handle the work that consumes your team’s capacity: tagging, modeling, analysis, reporting, and close.
q11 - Thomson Reuters, CoCounsel Tax
Explore the features that make CoCounsel Tax an AI tax research and document analysis tool built for firms of all sizes.
q12 - Vertex, Vertex AI agents
AI-powered automation operates directly within the Vertex Cloud platform to support indirect tax determination, e-Invoicing, global compliance reporting and file & pay workflows.
q14
Source: the makers' own pages, read 2 November 2026; notes 8 to 14.
3Limits and control questions
Tax positions in the financial statements are part of financial reporting. For a listed company, any automated step that feeds the financial statements sits inside internal control over financial reporting, which management must evaluate and report on; the SEC's interpretive guidance for that report is Release 33-8810.2 COSO describes its Internal Control, Integrated Framework as originally issued in 1992 and refreshed in 2013.3
Where a product uses a generative model to draft text, NIST has published a separate profile on the risks particular to generative AI, NIST AI 600-1.4 Ask how the product shows the authority behind each answer and how current its content is.
NIST's AI Risk Management Framework is a common reference for those questions. NIST says the framework is "intended for voluntary use and to improve the ability to incorporate trustworthiness considerations into the design, development, use, and evaluation of AI products, services, and systems."5 Its first version is published as NIST AI 100-1.6
Vendor claims about AI are claims, not findings. The SEC has brought settled charges against two investment advisers "for making false and misleading statements about their purported use of artificial intelligence (AI)."7 A finance team that relies on a vendor's description should ask for evidence of what the feature does with its own data.
4What filers say
A full-text search of SEC filings made between June 2025 and October 2026 found no filer describing AI in its own work on this task in words specific enough to quote. See how filings were searched.
Exhibit 9.2.Finance-software filers on their AI products
Listed software companies describing their own AI products to investors. These are the makers' statements, made in filings.
- Vertex, Inc. (VERX), Form 10-K filed 24 February 2026
During the second quarter of 2025, we completed our strategic investment in Kintsugi, a San Francisco-based, AI startup focused on automating sales tax compliance for small and mid-size businesses (the “Kintsugi Investment”).
F17
Source: SEC EDGAR full-text search; note 17.
5Products
Exhibit 9.3.Products addressing tax research and provision support, by the data they name
5 product records whose makers say they address this task, alphabetical by maker. Open a row for our summary, the data it names and the maker's words on review; the marks show which questions the maker's pages answer.
Avalara AI complianceAvalaraData it names: not stated.Where a person reviews: not stated.Model or data handling: not stated.
- Our summary
- Indirect tax compliance software with AI agents for tax calculation, returns filing and product tax classification. The maker says its classification AI is trained on a large catalogue of product items.
- Data it names (our list)
- Not stated on the pages read.
- Where a person reviews (quoted)
- Not stated on the pages read.
- Sources
- Notes 8,9. The full record for Avalara.
Blue J tax researchBlue JData it names: quoted.Where a person reviews: not stated.Model or data handling: quoted.
- Our summary
- A generative AI tax research tool that answers tax law questions in conversation and cites its sources. The maker says it uses models from OpenAI and Google and does not train on customer data.
- Data it names (our list)
- Primary authoritative content, Tax Notes, IBFD, Documents a user uploads
- Where a person reviews (quoted)
- Not stated on the pages read.
- Sources
- Notes 10,15. The full record for Blue J.
Intelligence Core, Lucanet LumeLucanetData it names: not stated.Where a person reviews: quoted.Model or data handling: not stated.
- Our summary
- AI agents in a finance and tax platform for tagging, modelling, analysis, reporting and close. The maker says each agent is built for a specific piece of finance work.
- Data it names (our list)
- Not stated on the pages read.
- Where a person reviews (quoted)
Lucanet Lume provides a single interface to query, instruct, and review.
q- Sources
- Notes 11. The full record for Lucanet.
CoCounsel TaxThomson ReutersData it names: not stated.Where a person reviews: not stated.Model or data handling: not stated.
- Our summary
- An AI assistant for tax research and document analysis, offered to firms and to in-house corporate tax teams.
- Data it names (our list)
- Not stated on the pages read.
- Where a person reviews (quoted)
- Not stated on the pages read.
- Sources
- Notes 12,13. The full record for Thomson Reuters.
Vertex AI agentsVertexData it names: not stated.Where a person reviews: quoted.Model or data handling: quoted.
- Our summary
- AI agents and in-app guidance for indirect tax determination, e-invoicing and compliance reporting. The maker says critical tax calculations stay on deterministic technology.
- Data it names (our list)
- Not stated on the pages read.
- Where a person reviews (quoted)
AI operates within governed workflows, with visibility into its use and human involvement where review, validation, and judgment are required.
q- Sources
- Notes 14,16. The full record for Vertex.
Source: the makers' own pages, read 2 November 2026; notes 8 to 16.
6Questions to put to a vendor
- What authority does the research tool draw on, and how current is it?
- Does every answer cite the source passage, and can we open it?
- Which model generates answers, and is our uploaded material used to train it?
- How does the compliance product separate AI suggestions from the deterministic tax calculation?
- Which decisions does the product take on its own, and which need a person's approval?
- How is a reviewer's change to an AI suggestion recorded?
- What does the vendor say about errors in answers, and what are the contract terms if one causes a loss?
- Which jurisdictions and tax types does it cover, and where does coverage stop?
Notes
- Internal Revenue Service, Office of Professional Responsibility and Circular 230. www.irs.gov/tax-professionals/circular-230-tax-professionals. Read 29 October 2026.
- U.S. Securities and Exchange Commission, Commission Guidance Regarding Management's Report on Internal Control Over Financial Reporting, Release 33-8810. www.sec.gov/rules/interp/2007/33-8810.pdf. Read 29 October 2026.
- COSO, Internal Control, Integrated Framework. www.coso.org/guidance-on-ic. Read 29 October 2026.
- National Institute of Standards and Technology, Generative Artificial Intelligence Profile, NIST AI 600-1. nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf. Read 29 October 2026.
- National Institute of Standards and Technology, AI Risk Management Framework. www.nist.gov/itl/ai-risk-management-framework. Read 29 October 2026.
- National Institute of Standards and Technology, Artificial Intelligence Risk Management Framework (AI RMF 1.0), NIST AI 100-1. nvlpubs.nist.gov/nistpubs/ai/NIST.AI.100-1.pdf. Read 29 October 2026.
- U.S. Securities and Exchange Commission, SEC Charges Two Investment Advisers with Making False and Misleading Statements About Their Use of Artificial Intelligence. www.sec.gov/newsroom/press-releases/2024-36. Read 29 October 2026.
- Avalara, Agentic tax and compliance | Avalara. www.avalara.com/us/en/products/ai-compliance.html. Read 2 November 2026.
- Avalara, Tax Compliance Software | Avalara. www.avalara.com/us/en/index.html. Read 2 November 2026.
- Blue J, Security | Blue J. www.bluej.com/security. Read 29 October 2026.
- Lucanet, CFO Solution Platform AI :: Lucanet. www.lucanet.com/en/platform/artificial-intelligence/. Read 30 October 2026.
- Thomson Reuters, CoCounsel Tax features | Thomson Reuters. tax.thomsonreuters.com/en/products/cocounsel-tax/features. Read 1 November 2026.
- Thomson Reuters, CoCounsel Tax for corporations | Thomson Reuters. tax.thomsonreuters.com/en/products/cocounsel-tax/corp. Read 1 November 2026.
- Vertex, Put AI to work for global tax compliance | Vertex, Inc.. www.vertexinc.com/solutions/ai-overview. Read 29 October 2026.
- Blue J, AI Tax Research Platform | Blue J - Start Free Trial. www.bluej.com/. Read 29 October 2026.
- Vertex, How Vertex uses AI in tax and compliance. | Vertex, Inc.. www.vertexinc.com/vertex-ai/ai-policies. Read 29 October 2026.
- SEC EDGAR, Vertex, Inc., Form 10-K filed 24 February 2026. www.sec.gov/Archives/edgar/data/1806837/000110465926019165/verx-20251231x10k.htm. Read 29 October 2026.
Other use cases: Forecasting, Accounts payable, Expense audit, Collections and cash application, Reconciliation, Close automation, Variance analysis, Contract and lease data, Treasury and FX, Payment anomalies and fraud, Audit preparation.