What an LLM sees when it looks at an ERP

Most enterprise software was designed for humans who’d been trained on it. ERPs in particular. NetSuite assumes you know which record type owns a field, which subsidiary a transaction belongs to, what “memorized” means in context. None of this is in the data — it’s in the operator’s head.

So what happens when you hand the keys to a language model?

I’ve spent a few weekends finding out. The vehicle is the Model Context Protocol — Anthropic’s open standard for letting LLMs call tools — and the patient is a NetSuite sandbox for one of Devma’s clients.

The setup

Claude gets three things:

1. A custom MCP server that exposes a curated set of SuiteQL queries and record-level reads.
2. A CSV-first lookup pattern for customers and items (faster than asking SuiteQL when the cardinality is small).
3. A system prompt that knows the customer-service workflow — how to take a phone order, when to ask for a PO number, what to confirm before submitting.

That’s the whole thing. There’s no fine-tune, no embeddings, no agent framework. Just MCP and prompting.

What works surprisingly well

The customer-service intake flow is the strongest demo. Claude can:

• Look up a customer by partial name or phone, disambiguating when there are multiple matches.
• Build a sales order line by line, validating items against the price list as it goes.
• Ask for the PO number at exactly the right moment — before submitting, not after.

That last one matters more than it sounds. A human CSR would just know. Teaching an LLM to know it took a sentence in the system prompt and zero code.

The part nobody warns you about

Custom MCP tools deployed via SDF ACP do not always surface in the NetSuite AI Connector’s /all endpoint on 2025.2. This is not documented anywhere I could find. The symptom is that your tool deploys cleanly, shows in the SuiteCloud project, and is entirely invisible to the connector.

The workaround is the SuiteApp deployment path. The lesson is the more general one: when an enterprise platform adds an AI surface, the AI surface is sometimes a thin veneer over older deployment plumbing, and the seams show.

The seams always show.

What it means

I don’t think we’re close to “agentic ERP” in the sense the marketing decks want it to mean. The hard part isn’t the model — the model is plenty capable. The hard part is that every ERP has hundreds of these unwritten conventions, and they all need to be coaxed out of the system one prompt at a time.

But that’s tractable. It’s not a research problem. It’s a careful enumeration problem, and it’ll get done.