We replaced 6 clicks with one chat message: a conversational ERP layer for ops, sales, and dispatch, no app, no IT ticket

This garment manufacturer's field sales team had the data. They couldn't get to it from the road. Every order status query meant 4 screens and 6 clicks, repeated through the day across a 6-person team. The ERP was fine. The data was there. Reaching it took a process designed for a desktop, not a car or a customer's counter.

We removed the navigation. Here's exactly how.

The client and the problem

A mid-sized garment manufacturer with multiple product lines, thousands of active customers, and an operations team managing production tracking, reseller ordering, and supplier coordination simultaneously. They had systems for everything. The records existed. What the field team lacked was a way to reach them at the moment a customer asked.

Three teams were affected:

• Customer service was navigating the ERP for every query: payment status, order status, delivery estimates. Each one: multiple screens, multiple clicks, every time.
• Marketing and sales needed commission data, sales totals, and customer purchase history, but always when they were away from their desks, on calls, or in meetings. The data existed; it just wasn't accessible in the moment they needed it.
• Operations needed order status and dispatch information on the go, and were constantly calling colleagues to get simple answers that should have been instantly available.

What we built: a WhatsApp-to-ERP conversational AI layer

A conversational operations layer: a natural language interface sitting on top of their live ERP and order management data. Teams send a message in plain English. The system interprets the query, retrieves the relevant data from the live systems, and responds in seconds.

The interface is chat: something every person on the team already uses. No new app, no login.

Before and after: conversational AI across customer service, sales, and operations

What this is (and what it isn't)

This is a natural language query layer connected to live business data: the same data that lives in the ERP, the order management system, and the CRM. When a team member sends a query, the system interprets the intent, retrieves the actual live record, and returns a plain-language answer. Unlike a FAQ system or chatbot, it does not answer from a knowledge base. In this deployment it reads from the ERP and does not write to it.

The system answers from the same data a human would look up with full ERP access. The answer reflects what the ERP holds at that moment and is specific to the exact record being asked about. When the query is ambiguous, it asks for clarification rather than guessing.

It does not correct a bad record. Ben Farrell, Global CEO of CIPS, said on Supply Chain Now in October 2026 that "how bad organizations are at data capture generally is the underlying thing that's interesting", and the show's own audience poll put poor data quality first at 39% (poll sample not stated). A query layer inherits the ERP's data quality, good or bad. What it does when a record is wrong or missing is a question we have not measured on this page.

What changed, and what we have not measured

These two figures describe adoption and footprint. They show the system is in use. They are not the return. The return would be a business result: calls to the office avoided, first-contact resolution on customer service calls, or hours a rep gets back to spend with customers. Alongside it sits a health figure: how often an answer was wrong or the system had to ask for clarification. This page does not publish a measured value for either, and we would rather say so than print a number we cannot trace.

What we can say is where the shift happened. It is less the time saved per query, which adds up across a field team that repeats the lookup all day, than that information became available at the moment of need rather than the moment of convenience.

A sales rep talking to a customer on the phone can now look up that customer's last order, outstanding balance, and recent purchase history while the call is happening, not by putting the customer on hold and finding a computer, but by sending a quick message on their phone. The quality of that conversation changes entirely.

Conversational AI in manufacturing: where it removes bottlenecks

The term "bottleneck" gets used loosely. In this deployment, it had a precise shape: information existed in the system, but reaching it required a person to stop what they were doing, open an application, navigate four screens, and return. Every single time.

For this client, that was an access problem rather than a missing-data problem. And it compounds across a team that repeats the lookup all day.

AI agents resolve this class of bottleneck by sitting between the question and the data source, interpreting natural language intent, routing the query to the correct live system, and returning a plain-language answer. The navigation layer disappears. The underlying ERP doesn't change. What changes is that the information reaches the moment of decision rather than the moment of convenience.

In this manufacturer's case, three distinct bottlenecks were eliminated simultaneously:

• Customer service stopped navigating to answer phone queries. They now respond while still on the call.
• Sales stopped waiting for end-of-week commission reports. They query live figures from their phone.
• Operations stopped relaying status via internal messages. Answers come directly from the system.

This is one deployment at one manufacturer. If your team reaches the ERP through the same screens, the same architecture applies; whether it fits depends on the queries your team repeats most.

Once one query type is handled (order status, in this case), the same architecture can be pointed at the next: payment confirmation, inventory levels, dispatch status.

If you run Business Central, check what you already have

This client ran a custom ERP, so none of the following applied to it. If you are on Business Central, Microsoft already gives you three routes to the same data:

Route	What Microsoft documents
BC data in Teams	Internal users licensed with qualifying Microsoft 365 plans, in an organization that has Business Central licences, "are granted read-only access to Business Central data from within Microsoft Teams, at no additional cost" (Microsoft licensing guidance)
BC app for Teams	Contact details, interaction history, and insights like outstanding payments or open documents (Microsoft Learn)
BC mobile app	Business data, charts and key performance indicators on a phone, with a BC sign-in (Microsoft Learn)

Test those first. Where a chat layer adds anything on top is something we scope with you; this deployment does not prove a gap on Business Central.

What's next for this client

In March 2026, when this case study was first written, the next phase scoped for this client was supplier invoice reconciliation: matching invoices against purchase orders and flagging exceptions, beyond answering questions about invoices. We have not updated that phase's status on this page since.

The pattern is worth copying even if the details differ. You start with one high-friction workflow, deploy a working system, and then the infrastructure and trust are in place to tackle the next one. This manufacturer started with an ERP query interface and scoped an AI agent for supplier invoices as the next problem, with the same team and the same infrastructure.

We've written separately about what happens after your first AI agent: the cross-department conversation that opens up once one workflow is running, and how teams begin codifying their own processes as Skills.

"It's amazing! This is so important for what I need while travelling."

Head of Sales, garment manufacturer

We've productized the conversational ERP layer from this deployment as AskOps, a standalone product that puts natural language queries on top of Business Central and custom ERPs today, with other ERPs on the roadmap. No new app, no login. For Dynamics 365 Business Central specifically, AskOps is also available as part of OpsGrid, our decision infrastructure layer for Business Central (active beta, delivered in Microsoft Teams).

Could your operations team use this?

If your team is navigating multiple screens to answer questions with simple, data-driven answers (order status, payment confirmation, inventory levels, customer history), the same architecture applies to your systems. The interface layer is generic. What changes is which data sources it connects to and what queries it handles.

We can scope this in a 60-minute call. We'll tell you which of your highest-frequency queries are best suited to natural language retrieval, which data sources need to be connected, and what a realistic deployment looks like for your environment.

Frequently asked questions