AI for ERP: how AI works with the ERP you already run

AI for ERP answers questions from the ERP that you already run and drafts entries for a person to approve.

Workers assemble parts at stations along a bright assembly line, with signal lights and air hoses hanging over each station

What AI for ERP means

An ERP, short for enterprise resource planning, is the business system that holds a company’s orders, inventory, purchasing, production, and accounting. You can keep the ERP as the system of record, which holds the official version of each record, and add AI on top. The AI layer reads the ERP data, answers questions about that data, and prepares work inside the ERP. The table shows the four jobs that the layer does and who signs off on each job.

JobExampleWho signs off
Answer a question“Which open orders for this customer will ship late, and why?” answered with the order numbersNo one, because the answer names the source records for anyone to check
Flag an exceptionA supplier’s price rose on the last three invoices, or an item’s on-hand quantity went negativeThe person who owns that supplier, item, or account
Draft an entryA sales order from a customer’s emailed purchase order, a purchase order from a reorder suggestion, or a supplier bill from an invoiceA named person approves the draft before the entry is saved or sent
Operate the screensAn agent keys an approved order into an older ERP the way a clerk wouldThe same approval, given before the agent types

One rule keeps AI for ERP safe. The AI sees only what the person asking may see, and the AI prepares only drafts. A named person approves anything that changes a record or leaves the building.

Answering questions with the source record

The right AI tool for ERP questions reads the ERP with your own permissions and names the source record in every answer. Many questions that people ask their ERP are lookups spread across several screens. Examples include what a customer ordered last year, which purchase orders are late, and what a part cost the last three times. An AI system answers such questions in one of two ways. One way is to write a database query from the question and run the query. The other is retrieval-augmented generation (RAG). AWS describes RAG as having a model reference “an authoritative knowledge base outside of its training data sources” before the model answers. AWS adds that RAG does this “all without the need to retrain the model.”

Either way, an answer about your business should name the source records, such as the order number, the invoice, and the receipt date. A number with no source cannot be checked. An assistant that reads the ERP through an administrator’s account can show anyone who asks the margin on every customer. So the answer should also respect who is asking. Microsoft’s MCP server for Business Central performs all operations “with your user identity and permissions, ensuring audit trails show who performed each action.”

An ERP AI chatbot built into the ERP answers from the ERP data only. A plant’s question often spans more, such as the ERP export, the customer’s email, and the drawing attached to that email. A data warehouse is one database that gathers data from several systems. A chat that answers from a warehouse holding all three sources can name the record behind every number, whatever system the record came from.

Red drive frames with rows of black rubber wheels and yellow pulleys run along a curved overhead conveyor track in a plant
A question about a late order is often a lookup across several ERP screens.

Drafting entries for a person to approve

Drafting targets the documents that people retype. Customer purchase orders are keyed as sales orders, supplier invoices as bills, and reorder lists as purchase orders. A customer set up for EDI (electronic data interchange) sends each purchase order as an X12 850 instead, which needs no retyping. AI reads the document, finds the customer, supplier, and items in the ERP, and fills in a draft.

The vendors that ship drafting build in the same approval. Microsoft’s Sales Order Agent “always involves designated Business Central users to review and approve all outgoing messages before it sends them to customers,” Microsoft says. The agent always creates a sales quote first, because quotes “have no impact on planning, reservations, availability calculations, or cash flow forecasts.”

Microsoft’s Payables Agent “creates drafts only and never automatically posts invoices.”

Four ways to connect AI to an ERP

How AI reaches your ERP decides what the AI can do and how much can go wrong. There are four routes, and many companies use two of them.

RouteHow the route worksGood forWatch for
API or MCP serverAn API (application programming interface) is the ERP’s own connection for other software. An MCP server is a connection built on the Model Context Protocol, an open standard for AI toolsReading and writing with the ERP’s business rules appliedUsually needs a cloud or recent version of the ERP. Check which records and actions are exposed
Read-only database connectionA reporting account reads the ERP’s database tables directlyFast answers and reports on an ERP installed on your own serverSkips the ERP’s business rules, so keep the connection read-only. Ask the vendor or your IT support first
Scheduled exports and importsThe ERP writes reports to files on a schedule, and approved entries go back through the ERP’s import toolOlder systems with good reportsAnswers are only as fresh as the last export
Screen agentSoftware reads the screen and uses the keyboard and mouse like a clerkOlder ERPs with no API, for keying approved entriesSlower than an API, and a person approves what the agent types

The Model Context Protocol (MCP) is “an open standard that defines how AI applications communicate with data sources and tools,” in Microsoft’s words. MCP matters because one connector can serve several AI tools. Microsoft’s documentation names Copilot Studio, GitHub Copilot, Claude, and ChatGPT as clients for the Business Central server. By default, the server “provides read-only access to all exposed Business Central API pages.” Write access needs a deliberate grant, page by page. Keep the same default on any ERP connection: read-only until a specific write is needed.

Shrink-wrapped pallets, stacks of blue drums, and racks of bottled goods fill a bright warehouse with yellow columns
System of recordThe ERP stays the system of record for stock and orders, whichever route the AI uses to read the data.

What the major ERP vendors ship

Microsoft Dynamics 365 Business Central, Oracle NetSuite, SAP, Sage X3, Epicor Kinetic, Infor CloudSuite, and Acumatica all build AI assistants or agents into their products. The descriptions in the table are the vendors’ own, checked September 28, 2026. Features change with each release, so check your version.

ERPWhat the vendor shipsIn the vendor’s words
Microsoft Dynamics 365 Business CentralSales Order Agent, Payables Agent, and an MCP serverThe Sales Order Agent “uses AI to analyze customer requests received via email and locates the customer in Business Central”
Oracle NetSuiteAI Connector Service and Bill Capture“NetSuite has adopted the Model Context Protocol (MCP), which boosts its integration capabilities and enables secure interactions between AI models and data systems”
SAPJoule Assistants“Joule Assistants use deep role and process context to coordinate AI agents and autonomously execute complex workflows across your business”
Sage X3Sage Copilot for Sage X3Starts with helping sales teams “query customer orders, shipping timelines, and fulfilment issues,” with questions asked in English, French, or Spanish
Epicor KineticEpicor Prism“Engage in natural language conversations with Epicor Prism to gather information, request insights, or execute actions”
Infor CloudSuiteInfor GenAI assistant“a conversational assistant enabled with industry-specific AI agents,” embedded in Infor CloudSuites
AcumaticaAI Assistant and AP (accounts payable) document recognition“The Acumatica AI Assistant helps employees ask questions about business data in plain language”

Three questions apply to every vendor. First, how is the AI billed? Microsoft bills selected Business Central agents per use in Copilot Credits, through prepaid capacity or pay-as-you-go. Microsoft’s billing documentation explains the model. Ask every vendor for the billing model, and check the vendor’s own pricing page. Second, which records and actions can the AI reach, and under whose permissions? Third, where are prompts processed? Microsoft’s Payables Agent FAQ covers environments in regions where Azure OpenAI is not available. In those environments, “administrators must allow data to move across geographies.”

Which route fits your ERP

Tell us which ERP you run, which version, and where the ERP is hosted. We will tell you which of the four routes the ERP supports and what AI can do through each route.

Derik Lawlis, founder
Start a conversation

What to do when your ERP has no API

If your ERP was installed on your own server years ago and has no modern API, the vendor’s cloud agents are usually out of reach. AI can still work with that ERP.

  1. Ask the vendor or reseller what exists. Some older systems have an add-on API, an ODBC driver, or an import tool that nobody at the company has used. An ODBC driver is a standard way for reporting tools to read a database.
  2. Read from a copy. A read-only database connection, or a nightly export of the reports that people already use, is enough for questions, answers, and exception flags.
  3. Write back through the screens, with approval. A computer use agent, software that works the screen, keyboard, and mouse like a person, can key approved entries. Anthropic describes the computer use tool as providing “screenshot capabilities and mouse/keyboard control for autonomous desktop interaction,” and recommends precautions. One precaution is “Asking a human to confirm decisions that might result in meaningful real-world consequences.”
  4. Keep the ERP as the record. Whatever the route, the ERP stays the system of record. The AI layer logs what the AI read and drafted, and who approved each draft.

Running AI next to an old ERP also records the questions that people ask and the documents that they retype. That record is a useful list of requirements if you later replace the ERP.

Close-up of the four-jaw chuck on a tube cutting machine, holding a steel tube, with warning labels on the chuck face
An ERP installed years ago can still feed AI through a database copy, report exports, or a screen agent.

Where to start

Pick one job with a clear before and after. Two kinds of job make good first projects. One is a question that someone answers by hand every day, such as late orders or stock for a customer. The other is a document that someone retypes every day, such as customer purchase orders or supplier invoices. Measure the time and the error rate for a month by hand. Then measure again with the AI drafting and a person approving.

How ThriveAI helps

ThriveAI is an AI engineering company in Ottawa that builds private AI systems for manufacturers in Canada and the United States. Each system runs on the client’s own data. ThriveAI works with the ERP that a company already runs, through whichever route that ERP supports, including screen agents for older systems. Each answer names the source record, and drafts go to a named person for approval before anything is saved or sent. Each client has a copy of the data reserved for the client’s team. ThriveAI hosts that copy, or the client hosts the copy on its own servers. The client chooses a model where the copy is hosted or a hosted model under a written zero data retention agreement. Under that contract, the provider keeps no copy of a request or of the answer. A hosted model may process requests in another country. Derik Lawlis, the founder, leads every project and stays close to the build. For more information, see About ThriveAI.

Questions people ask

What is AI for ERP?
AI for ERP is software that reads the data in the ERP that you already run. The software answers questions with the source record, flags exceptions, and drafts entries for a person to approve. Typical drafts are sales orders, purchase orders, and supplier bills. The ERP stays the system of record.
Does my ERP need an API to use AI?
No. An API or an MCP server is the cleanest route. AI can also read from a read-only database connection or from scheduled report exports. To write entries into an older ERP with no API, a computer use agent can key approved entries through the ERP's own screens.
Can AI enter data into my ERP?
Yes, through an API, the ERP's import tool, or an agent that uses the ERP's screens. In a safe setup, AI drafts each entry, and a named person approves the draft before anything is saved. Microsoft's Business Central agents follow this pattern: the Payables Agent creates drafts only and never posts an invoice automatically.
Which ERPs have AI built in?
As of September 2026, all seven ERPs in this guide ship AI assistants or agents, according to each vendor. The seven are Microsoft Dynamics 365 Business Central, Oracle NetSuite, SAP, Sage X3, Epicor Kinetic, Infor CloudSuite, and Acumatica. Features, pricing, and availability differ by product and version, so check the release that you run.
What is an MCP server for an ERP?
MCP, the Model Context Protocol, is an open standard that defines how AI applications communicate with data sources and tools. An ERP's MCP server lets AI tools such as Claude or ChatGPT read the ERP data. The tools can also take actions if an administrator allows those actions. Microsoft's Business Central server is read-only by default.
Is it safe to connect AI to our ERP?
Uploading an ERP export to ChatGPT sends a copy of that data to OpenAI's servers. Before uploading, check the plan's terms on training, retention, and where the data is processed. A direct connection to the ERP can be safe with three controls. Give the AI only the permissions of the person asking, or read-only access, so the AI sees and changes no more than that person. Have a named person approve every entry before the entry is saved or sent. Keep a log of what the AI read, drafted, and changed, and ask where your data is processed.

Contact

Get more out of the ERP you already run

Tell Derik which ERP you run and which question or document takes your team the most time. He will tell you how AI would reach that data and what it could draft for your team to approve.

Prefer to talk? Book a meeting.

Your message goes to Derik Lawlis, the founder.