[ erp system × ai agents ]
A full open-source ERP, exposed entirely as an MCP server and therefore completely operable by AI agents. In the pilot business, a butcher shop with a counter, vending machines, and an online shop, employees say what they need in plain language; the agents do the work in the systems. This page shows how the system was developed, the decisions behind it, and the experience gathered along the way.
Agents with system access and skills do the work inside the system.
Several mechanisms secure agent operation in the real world.
Integrated as an MCP server so agents know what to do.
Setup and interaction along the value chain, in natural language.
[ system operators of the future ]
The common expectation goes: once AI agents take over the work, business software becomes obsolete. My experience from this project is the opposite. The more an agent does on its own, the more important the system underneath becomes. It delivers exactly what a language model cannot: it enforces completeness, because an incomplete transaction simply does not happen. It ensures consistency, because bookings are interconnected. And it produces the audit trail as a byproduct.
An agent working next to the systems invents its own truth. One working inside them cannot. The roles shift: the human becomes the decision maker, the agent the operator, and the system remains the source of facts. That is why, to me, the systems with their rules and limits are themselves a governance mechanism.
[ the full value chain, end to end ]
Deploying individual AI agents in isolated corners is not the challenge; it is how island solutions get created in the first place. The value emerges when the technology integrates along the entire value chain and the agents hand tasks to each other as specialists.
[ Sales ]
The sales agent has access to the sales data of all channels and uses a forecasting model to create the daily demand per article, enriched with weather and holidays. Before: numbers from several systems have to be collected and copied into spreadsheets by hand.
[ Production ]
The production agent traces the forecast demand back through recipes and BOMs to raw materials, creates the weekly plan, and books the confirmations. Before: planning by experience, confirmations on paper at closing time.
[ Purchasing ]
The purchasing agent creates orders: supplier, quantity, date, and terms from history and framework contracts. What it can prove from data goes through; what it can only assume goes to the employee as an approval. Before: phone calls, shouts across the room, and typing it in later.
[ Warehouse ]
The warehouse agent books goods receipts, monitors stock, batches, and expiry dates, and reports coverage. Before: counting lists on paper and manual transfer.
[ Finance ]
The finance agent monitors open items and prepares reports. Before: typing up stacks and end-of-month rush.
[ HR ]
The HR agent puts the demand forecast next to the shift plan and absences: how much needs serving tomorrow, who is out, who can fill in where. Staffing emerges from numbers already in the system. Before: a pinboard and a phone chain for every sick call.
[ architecture ]
Keeping the layers strictly apart was the most important architectural decision: governance sits in a layer of its own that no agent gets past. And the business logic is not rebuilt, it is used.
Natural-language interaction with the supervisor agent
A supervisor plans, distributes the work to specialized subagents, and merges the results. The knowledge lives in versioned skills that are loaded only when needed: small context, lower cost, any number of capabilities.
Why LangGraph: a fixed plan of execution, permanently stored intermediate state, built-in interruptions for human decisions. An approval can take three days. A conversation thread does not survive that; a stored state does.
Still: the framework is not the core. The logic lives outside it and stays replaceable when the next generation of tooling arrives.
Rules secure the agents' actions
Every agent action passes through the gateway; there is no way around it. What an agent may do is defined. What it does is logged without gaps. What is uncertain goes to a human as an approval card. Operation stays safe even when a model gets it wrong.
The tool index lives here too: the gateway discovers the entire ERP surface and makes it searchable. No model finds the right function in a flat list of thousands of entries. So the agent works with two tools: one searches the matching function, the other executes it.
Executed actions happen directly in the system
The open-source ERP runs unchanged in its standard form and stays updatable at any time. Over 3,400 standard functions are available to the agents without touching the system: the gateway does the discovery.
The business logic does not have to be rebuilt, it is already there. Required fields, checks, and booking rules act as a built-in guardrail: a transaction only happens when all information is complete.
[ perspective ]
Today's language models and agent technology can already do a lot. Waiting for the next bigger or more expensive model adds no further value in my view: the capabilities are sufficient when architecture and data foundation are right.
The real bottleneck sits in the data and systems. Anyone who never got them into decent shape for people will find it far harder to get them ready for language models. The standards exist and are available, MCP above all. So far, the use cases and solutions on the market barely build on them.
How much easier it gets with these standards shows in the setup: because the agent reaches the full range of functions via MCP, it helps with the setup and the master data itself. In an internal test, a complete business was up and running after twelve messages in the chat. And in daily operation, the agents support along the entire value chain, directly in the systems.
[ numbers ]
over 3,400
standard ERP functions and document types, exposed for AI agents
~95%
reliability in choosing the right tool, no hallucinations
any model
usable, chosen cost-efficiently per type of task, automatically in the system
∞ AI agents
and skills definable without managing each one: the skill carries the knowledge
[ technology ]
Wondering how this technology could create real value in your business? Then let's talk: you bring the challenge, I bring the experience and the tools.
