Chapter 02Agentic AI and ERP
AI agents inside the production flow
An order arrives as a PDF, a delivery route gets planned in a spreadsheet, a quote is priced over the phone. Between those steps, people retype, double-check and chase. An AI agent takes over those handoffs: it reads, queries the systems, prepares the decision and puts it in front of the right person. It also gets maintenance and production working in the same CMMS.
Today
A process built around the ERP
- PDFThe order arrives by email.
- ERPAn assistant retypes it into the ERP.retyping
- SpreadsheetThe schedule is exported to a spreadsheet.copy
- EmailThe shop floor gets the schedule by email.handoff
- PhoneA slipping lead time gets fixed over the phone.chasing
4 manual handoffs, and nothing flows back: an error corrected today happens again next week.
With an agent
An agentic workflow that learns
Receive
the order, whatever its format
Read
customer, part numbers, quantities, requested date
Cross-check
against the ERP, the stock and the schedule
Propose
a confirmed lead time, a work order
Approve
a person accepts or corrects it
Act and log
the ERP is updated, everything is logged
The feedback loop
Every correction made at approval becomes a rule, with its source and its author. Next time, the agent applies it.
Maintenance and production in the same CMMS
In many plants, maintenance and production each organize their own side: the CMMS (the maintenance management system) on one side, the production schedule on the other, with phone calls and spreadsheets in between. An agent can get them working from the same information.
Everything lands in the CMMS
A sensor signal, a PDF service report, a thermal image, a message from an operator: the agent reads them and attaches them to the right piece of equipment in the CMMS, instead of leaving them in inboxes.
The work order gets prepared
The agent opens the work request, checks the spare parts in the ERP and pulls together the machine’s history.
The stop fits the production schedule
It proposes a slot for the stop that takes the production schedule into account, rather than a breakdown in the middle of a run.
Both teams decide together
The shop supervisor and the maintenance manager approve the same proposal, and every choice stays on record in the CMMS.
Workflows at every step of production
A production process is a chain of workflows: at every step, information passes from one person, department or piece of software to the next. Those handoffs are still often done by hand, by email, spreadsheet or phone. That is where an agent has the most to do.
Orders
receiving, entering, confirming lead times
Planning
scheduling, assigning workstations and crews
Purchasing
chasing suppliers, receiving goods, matching invoices
Manufacturing
work orders, changeovers, instructions at the workstation
Quality
nonconformities, inspection sheets, customer complaints
Maintenance
work requests, spare parts, service reports
Shipping
picking, delivery routes, transport documents
Invoicing
invoices, reminders, credit notes
Data in every shape
PDF · scan · photo
Documents
Orders, delivery notes, service reports, drawings: the agent reads them the way a person would, with no template to set up.
sensors · logs
Signals
Sensor readings, cycle times, quality measurements, machine logs.
email · WhatsApp · calls
Conversations
Exchanges with customers, suppliers and teams, which is often where the real priorities get set.
cameras · inspection
Images
Photos of defects, thermal images, visual checks on packaging.
Anatomy of an agentic workflow
The same sequence shows up from one plant to the next. What changes is the data, and who signs off.
Receive
An order, a message, an alert.
Read
The agent pulls out what matters, whatever the format.
Cross-check
It queries the ERP, the stock, the history.
Propose
It drafts a reply, a schedule, a quote.
Approve
A person accepts, corrects or rejects it.
Act and log
The action goes out, and everything is logged.
A harness the company owns
Around the AI model, an agent rests on a harness: its instructions, the business rules, its access to software, the checks and the log of what it does. We build it methodically, documented and versioned, inside your systems, and the company keeps full ownership of it. It can change model or provider without starting over, which makes it resilient. Its teams can also change a workflow as soon as the need shifts, and that is what gives it agility.
Work in progress
At an industrial joinery manufacturer we have worked with since 2025, the open workstreams cover the whole chain:
- Ordersreading the orders that come in as PDFs
- Logisticsassigning delivery routes
- Salespricing quotes through a conversation on WhatsApp
- Qualitya quality indicator
- Shippingpackaging
What we deliver
Tools that run on your side
The goal is agents that work on their own inside your teams, on your data.
Partner engineering
Gilles Babinet leads the strategy; partner engineers build and deploy.
Trained teams
Training days so your people can use the agents, correct them and make them evolve.
Support over time
A year-long engagement rather than a one-off deliverable: workflows change, and the agents keep up.
Let’s talk about your production flows
Tell us where information gets lost between two steps, and we will get back to you to set up a first conversation.