How to send WhatsApp messages from QNE (the no-wait way)

QNE's in-product AI is a good assistant for the work that lives inside QNE. The WhatsApp front door is a different layer — the layer that reads the QNE ledger and writes the answer into the channel the customer is actually using. The Meta Embedded Signup process takes 2 to 4 weeks, and the no-wait path is the same one the SQL Account users, the AutoCount users, and the QuickBooks users are already on. Here is what it looks like for QNE.

Why the BSP route is slow

The standard advice for a Malaysian business that wants to send WhatsApp from QNE is: sign up with a Business Solution Provider, get a WhatsApp Business API number, and let the BSP handle the Meta verification. The advice is not wrong. It is just slow. A typical flow is: choose a BSP, sign a 12-month contract, get a number ported or a new number assigned, submit the Meta Business verification, wait for the Meta review team, fix whatever the review team flags, get the API credentials, build the integration to your QNE. Six to eight weeks, conservatively, before the first message lands.

The reason it is slow is not the BSP's fault. The reason is that the verification, the number, the API credentials, and the integration are four separate things, and most BSPs do not own all four. The verification is Meta's. The number is Meta's. The API is Meta's. The BSP owns the markup, the contract, and the support queue. The integration to your QNE is yours — and QNE has an API, which is the easy half. The hard half is the BSP, and the BSP is the slow half.

What Embedded Signup actually is

Meta's Embedded Signup is the official flow for letting a software platform — like minidesk — connect a business's WhatsApp number to the Meta Business API without the business leaving the platform. The flow is: the platform opens a Meta-hosted signup window, the business picks the WhatsApp number they want to use, Meta verifies the number belongs to the business, the platform gets the API credentials, the conversation window opens. The whole thing, when the platform holds a Meta Business verification, takes about ten minutes.

The slow part is the verification. Meta wants to know that the business requesting the API access is a real business, with a real website, and a real reason to send WhatsApp messages. The verification is what stops a spam operation from buying a thousand numbers. The verification is also what most platforms do not hold, and what every BSP waits on. When a platform holds the verification already, the business does not have to apply for it. The platform already proved to Meta that the use case is legitimate. The business just has to prove the number is theirs.

The plug-in path: QNE + minidesk + WhatsApp, in 20 minutes

minidesk holds the Meta Business verification. When you sign up and pick QNE as your connector, three things happen in parallel: you click the OAuth to your QNE account, you connect your business WhatsApp number through Meta Embedded Signup, and you authorise the AI to read the QNE data. The first message you send can be a template ("your invoice INV-XXXX is now due"), or it can be a free-form message the AI writes based on what it read in QNE ("Hi Encik Lim, your July order is ready for collection. Outstanding balance: RM0. New order welcome."). The choice is yours; the connector does not care.

The OAuth is one click in the QNE consent screen. The Embedded Signup is one Meta-hosted window. The AI is the same AI that runs every other connector on minidesk — once QNE is connected, the AI knows how to read it, and the message goes out in the customer's language, with the right invoice number, with the right amount, in the right currency, on the right day. Your in-product QNE AI keeps doing the work it was already doing. The two AIs do not compete; they answer different questions.

What the conversation looks like in practice

A B2B customer in Puchong — a corporate catering regular who orders RM 3,200 of finger food every month — sends a WhatsApp at 8:14am on a Monday: "Any update on INV-2025-07412?" The AI reads the QNE invoice record, sees the deposit landed on Friday, and replies: "Hi Puan Lim, INV-2025-07412 for RM 3,200 was paid on Friday. Your account is up to date. Let me know if you need the receipt resent." The reply lands at 8:14:18am. The customer reads it before the 9am standup. The finance team sees the thread, the customer is happy, the morning starts on the front foot.

“We were paying a BSP RM 1,500 a month and we still had to type the WhatsApp messages ourselves. Now the AI reads the QNE, writes the message, and shows me the queue. I just approve. The QNE in-product AI still does the in-product work — the two AIs do different jobs.”

— Hafiz, who runs a small IT distribution business in KL

What to do if you are already on a BSP

If your business is already on a Business Solution Provider — WATI, SleekFlow, AiSensy, Twilio, MessageBird, or any of the long tail — the good news is the WhatsApp number and the API credentials are already in your business name, and Meta has already verified you. The migration is the part you are weighing, not the setup. The practical path is: keep the BSP contract running for one billing cycle while you set up minidesk in parallel. Connect your QNE, connect your WhatsApp, and let the AI read your data. Test the AI on a small set of conversations — say, the top 10 customers by balance — and compare the messages the AI drafts to the messages your BSP has been sending. When you are comfortable, switch the routing over and cancel the BSP at the next billing date. The Meta-side change is a settings switch, not a re-verification.

Common mistakes when you set this up yourself

Three mistakes we see most often, all worth naming. (1) Connecting a personal WhatsApp number instead of a business number — Meta does not allow a personal number on the Business API, and the porting process is a separate project. (2) Trying to set this up before the chart of accounts is clean — the AI reads what is in the ledger, and a chart of accounts full of one-off accounts makes every answer longer than it needs to be. (3) Skipping the test phase — the first WhatsApp the AI sends should go to your own number, so you can see the layout, the language, the speed, before it goes to a customer. We have made all three of these mistakes ourselves; that is why the install wizard walks you through each one.

What it costs (and what it does not)

The Meta conversation fees are the same fees every platform pays. minidesk does not add a per-message markup on top of Meta's. The plan is a flat monthly fee that includes the AI, the channels, the OAuth, and the WhatsApp API. No per-conversation surcharge. No 12-month contract. No setup fee. The pricing is on the website; the quote is the quote.

If your business is already on QNE, the WhatsApp path is the part of the second layer of AI you will use the most, and it is the part that takes the least time to set up. Twenty minutes from signup to the first message. The bookkeeper does not have to do anything different. The customer does not have to download an app. The message lands in the WhatsApp they already have open.

→ See the QNE integration: /integrations/qne