AI enablement: from the first sessions to agents in production
We train teams on the company’s own documents and processes, automate repetitive tasks and connect agents to the ERP. At the end, the company knows how to maintain and evolve what is up and running.
| Task | repeated | reversible | low value | rule-checkable |
|---|---|---|---|---|
| Matching invoices to orders→ chosen | ● | ● | ● | ● |
| Replies to quote requestsnext | ● | ● | ◐ | ● |
| Contract summarieslater | ● | ● | ◐ | ○ |
| Supplier paymentsstays with a person | ● | ○ | ○ | ● |
- 01usage policy approved by the board
- 02hands-on training for the finance team
- 03pilot with a €2,000 limit
- 01
With the company’s own cases
Training and workshops on each area’s documents and processes.
- 02
One measured task first
The first automation shows results before it is extended.
- 03
It stays with the company
Rules, prompts and settings documented and held in the company’s account.
Who it is for
Teams already using AI without rules
People using AI assistants on their own, without knowing what data they can put in or where it is kept.
Document-heavy areas
Contracts, manuals, invoices, manifests and support history that someone reads and summarises every day.
Finance and purchasing in the ERP
Matching invoices to orders, recurring postings and reconciliations that currently pass through several hands.
Management teams that want to start with a measured task
The first automation has to show results before it is extended.
How the company maintains what is up and running
What stays with the company
The usage rules, prompts and agent settings are documented and held in the company’s account.
Who makes changes
The internal team learns to adjust prompts and limits. Whoever maintains integrations can use Claude Code on their own code.
Limits change with the track record
Reviewing the limits is part of the follow-up.
Support
The team that delivered the project stays on support.
What it includes
Applied training
Hands-on sessions on each department's documents and processes, using the company's own cases.
Process workshops
We go through each area’s repetitive tasks and choose those that are reversible, low in value and verifiable by rule.
Usage policy and governance
Usage rules, classification of sensitive data, logging of interactions and configuration of admin controls.
Process automation
Assistants over internal data, citing the source, and document processing (invoices, manifests, delivery notes) through to posting in the source system.
Agents connected to the ERP
Agents that read and propose postings in Sage X3 and Cegid PRIMAVERA via MCP, with the permissions of the user who invokes them.
How it works
- Assessmentwe go through the processes and choose the first task
- Usage policyrules, sensitive data and Claude administration controls
- Applied trainingsessions by area, using the company's own cases
- First agenta reversible, low-value task verifiable by rule, with low limits
- Limit reviewautonomy increases when proposals are approved without correctionsafter weeks of history
Further reading
AI agents connected to the ERP: where it is safe to let them decide
Value limits, permissions inherited from the user and the design of the human validation queue.
An agent that looks for VAT errors: what it needs to know about each country
In September Cegid showed an agent that diagnoses the VAT settlement. An agent like this is only as good as the rules it knows, and the rules change from country to country.
Choose the first task for AI
We go through your processes with you and choose a task that is repetitive, reversible and verifiable by rule.
Got a project? Let us talk.
Answer within 24 working hours.