NEWSRegister for our 25 Nov in-person event in Singapore on NGO and non-profit financial governance!

Ask NetSuite a question. Get a number that ties out.

We connect Claude or ChatGPT to your NetSuite account with its own read-only role, test it in your sandbox, and check its answers against your own reports. AI prepares it. Your team approves it.

Trusted by finance and operations leaders at
3DoodlerDiginexAMPD EnergyFloshipKidKraftGoProShanghai Tang
The problem

The demo looks great. Then someone asks if the number is right.

Connecting an AI assistant to NetSuite takes an afternoon. Trusting what it says about your books is the part nobody shows you.

One question, two answers
Finance asks

What was Q3 revenue for the whole group, in HKD?

The assistant saysHK$12.4MDoesn’t show the scope or rate it used
The NetSuite report saysHK$11.9MConsolidated income statement, same scope as the question
HK$0.5M apart

The question and the report cover the same scope: every subsidiary, in HKD, July to September. The assistant doesn’t show what it used, so nobody can say which figure is wrong.

What it can reach, and who checks the answers
Pasted data

Only what someone pastes in

Self-checked · by whoever typed it in
File exports

A snapshot from the day it was run

Unchecked · needs the source file and its date
Live read access

Every subsidiary its role can see

Unchecked · needs scope, currency and period shown
Write access

Can create and change records

Unchecked · needs a named approver

A safe integration needs scoped access, traceable answers and approval for write actions.

How it works

Data first, then AI. Read-only before anything else.

One fixed scope, agreed before we start. You see what the assistant gets right and wrong in your sandbox before it goes near production.

Start with a scoping call
1

Pick the job

We start with one thing that is painful this month: bills retyped from PDFs, a report rebuilt by hand every close, questions that wait a week for a saved search. The setup is scoped around that job.

Use-case scopingWho will use itFixed scope
2

Check the data it will read

An assistant repeats whatever is in the records. We look at the chart of accounts across entities, duplicate vendor names and intercompany mapping, and tell you what needs tidying before the answers can be trusted.

Data reviewVendor clean-upEntity mapping
3

Build a read-only role

The connection gets its own role, never an administrator login. It sees the records the job needs and nothing else, and it cannot create, edit or delete. We handle the connector permissions and single sign-on along the way.

Dedicated roleConnector setupAccess review
4

Test in sandbox against your own reports

Your team writes ten questions it already knows the answers to, by period and by subsidiary. We run them in sandbox and put each AI answer next to the matching NetSuite report. You see what ties out and what doesn’t.

10-question test setSandbox firstResults you can audit
5

Teach it your calendar and your group

Most wrong answers come from the assistant not knowing your fiscal periods, your consolidation structure or your base currencies. We write those rules down for it, then run the test set again until the answers match.

Period rulesConsolidation rulesRetest
6

Go live, then add drafting

Read-only questions go to production first, with your team trained on what to ask and what to double-check. Drafting, such as supplier bills prepared for approval, is a second scope. Every draft waits for a named person.

Team trainingProduction rolloutOngoing support
The controls

AI can prepare the work. It can’t approve it.

Read-only to start

The first stage can look and answer. It cannot post, edit or delete, because the role it runs under doesn’t allow it.

A named person approves

When drafting is switched on, each draft sits next to its source document until someone on your team signs it off.

An audit trail your auditor can read

The connection has its own role and login, so its logins and anything it drafts are on the record, separate from what your people did.

Somebody answerable

You get a written note of what the assistant can see, what it was tested on and where it was wrong, with a consultant’s name on it.

Oracle NetSuite Partner of the Year 2025Oracle NetSuite Partner of the Year 2024Oracle NetSuite Partner of the Year 2023Oracle NetSuite Partner of the Year 2023Oracle NetSuite Partner of the Year 2022Oracle NetSuite Partner of the Year 2021Oracle NetSuite Partner of the Year 2021
What changes

The work around NetSuite goes. The numbers stay in it.

Supplier bills retyped from PDFsExports rebuilt in Excel every closeQuestions emailed to financeOne-off saved searches nobody reuses
Oracle NetSuiteAnswers from your own recordsRead-only role · Sandbox tested · Checked by period

The assistant reads NetSuite through a connection Oracle provides. It doesn’t keep a second copy of your books, so there is one set of numbers to check.

01

Questions answered without a saved search

Ask in plain English and get the figure with the records behind it, so anyone can click through and check.

02

Bills drafted, not retyped

The assistant reads the supplier document and prepares the bill. Your AP team checks the exceptions and stops keying in the rest.

03

Saved searches and reports drafted for you

Describe what you need and get a first version to review. Your admin spends their time checking it, not building it.

04

Group answers that respect the structure

Consolidated or by subsidiary, in the right period and currency, because the assistant has been told how your group is built.

05

A short list of what not to ask it

Where the test set shows it can’t be trusted yet, we say so in writing. That list is as useful as the list of what works.

06

Your own scripts and prompts reviewed

Already built something with Claude or ChatGPT? We’ll review it and keep what’s sound. We don’t start again for the sake of it.

Have one job in mind that eats a day every month? Tell us what it is.Scope an AI use case
Built for Hong Kong books

Tested on HKD, RMB and USD, not just a single-currency demo.

Most AI demos run on one entity in one currency. Your ledger doesn’t look like that, so the test set doesn’t either.

More than one subsidiary

Questions are tested per entity and consolidated, so a group total is never one company’s figure by mistake.

More than one currency

We check that amounts come back in the currency you asked for, at the rate NetSuite used, for HKD, RMB and USD books.

Your periods, not calendar months

Fiscal year-ends, adjustment periods and locked periods are written into the instructions the assistant works from.

Dates the right way round

Day-month-year dates are a known source of wrong answers. They go in the test set from the start.

Two names for the same vendor

English and Chinese versions of one supplier are matched up during the data review, before the assistant double-counts them.

Available here today

This setup uses NetSuite’s AI Connector, which doesn’t depend on NetSuite Next. Oracle hasn’t published a Hong Kong date for Next.

Who it’s for

Two readers, two sets of questions.

Finance wants to know what the assistant can’t do. Admins want to know exactly how it’s wired.

You sign the accounts, so the question is control.

The assistant starts with read-only access, its answers are checked against reports you already trust, and nothing reaches the ledger without a person approving it.

Talk through the controls
What you get
  • A test set your own team wrote, with the results
  • A written list of what the assistant can and can’t see
  • Approval by a named person for anything drafted
  • A separate login, so its activity is on the record

You do the retyping.

The aim is fewer keystrokes on routine bills and more time on the ones that don’t match, with the source document on screen beside every draft.

Scope an AP use case
What you get
  • Supplier bills prepared from PDFs for review
  • Exceptions flagged instead of buried
  • Drafts routed to the right subsidiary
  • Training on what to check before approving

You’ll own it afterwards, so here is the wiring.

NetSuite’s AI Connector Service (its MCP server), a custom non-administrator role, OAuth 2.0, and a sandbox run before production. Your AI subscription is your own.

Ask a technical question
What you get
  • Custom role with MCP Server Connection, OAuth 2.0 and REST Web Services permissions
  • SAML single sign-on handled alongside the connection
  • Instruction files for periods, subsidiaries and consolidation
  • A review of scripts and searches you’ve already built with AI
We have been really impressed by ONE Pacific’s responsiveness and your knowledge within the finance automation space.
Paul EwingChief Financial Officer, Diginex

What finance teams ask before they connect AI.

Straight answers, including the ones where the answer is “not yet”.

Ask a consultant
What it does
What can AI actually do with our NetSuite data today?+

Three things are worth setting up now: answering plain-English questions from your own records, drafting saved searches and reports for someone to review, and preparing supplier bills from documents for a person to approve. Each one needs testing against your own reports before you rely on it. Letting a model post transactions on its own is not something we set up. Our review of what works and what doesn’t goes through the detail.

Does it work with Claude, ChatGPT or both?+

NetSuite’s AI Connector is built on an open standard, so it isn’t tied to one assistant. You bring your own subscription. On the scoping call we confirm which assistants your NetSuite account and your IT policy support before you commit to anything.

Our admin could connect this in an afternoon. Why involve a partner?+

They probably could, and for a first look that’s fine. The connection is the easy part. The work is in what the assistant is allowed to see, whether its answers match your reports across subsidiaries, currencies and periods, and who is answerable when it’s wrong. That is what the role design and the test set are for. If your admin has already built something, we’ll review it instead of redoing it.

Safety and control
How do we know the numbers are right?+

You check them, with us, before go-live. Your team writes ten questions it already knows the answers to. We run them in sandbox and put each AI answer next to the matching NetSuite report, by period and by subsidiary. Where it’s wrong we fix the cause or tell you not to use it for that question.

Can it post or change transactions?+

Not in the first stage. The connection runs under a read-only role, so it can’t. Drafting comes later as a separate scope, and every draft waits for a named person on your team to approve it.

What does the AI provider see, and where does our data go?+

Only what the dedicated role can see, and only when someone asks a question. We write a short data-handling note for your account: which records are in scope, which provider plan you’re on and what its retention terms are. It doubles as the written policy on what staff may put into AI tools that Hong Kong’s Privacy Commissioner recommends. For groups with Mainland entities, we flag the data that should stay out of scope.

Do we need a sandbox?+

We strongly prefer one, because it lets you see mistakes where they cost nothing. If you don’t have a sandbox, tell us on the scoping call and we’ll go through the options.

NetSuite’s own AI
Do we need NetSuite Next for this?+

No. The AI Connector is separate from NetSuite Next. Oracle is releasing Next in North America first and hasn’t published a Hong Kong date; we track it in our note on timing. We’ll also tell you which of NetSuite’s built-in AI features are worth switching on in your account, and which aren’t yet.

What does it cost?+

There are two parts. Your AI assistant subscription is paid to the provider directly. Our setup is a fixed scope with a price agreed before we start. Oracle doesn’t charge for the AI Connector itself, and using it doesn’t draw on your AI Units. Some of NetSuite’s own built-in AI features are metered separately, and we’ll check what applies to your account instead of guessing.

Bring one job. We’ll tell you if AI can do it.

Tell us the task that eats the most time. In 30 minutes we’ll say whether an assistant can take it on safely in your account, and what we’d test first.

OnePac’s team provided vision and perspective on how long it should take or what we should really think about the path forward.
Jim ToernqvistSystems Director, WobbleWorks
It’s in Hong Kong
Ask usanything