You drop in your key documents
A dozen documents are enough to describe a company: org chart, offers, business model, master procedures.
Plugged into your Kastel, the AI answers with your data.
“What is our customer refund window, and who can make an exception?”
What your Kastel holds
A structured representation of your company that any AI can read.
The organisation
The departments that actually exist, who does what, who reports to whom.
The processes
How the work really gets done at your company: the real procedure, exceptions included.
Permissions
Who is allowed to see what, and who a request goes to for approval.
The entities
Clients, projects, suppliers, products. Linked to each other and never duplicated.
The memory
The decisions taken, their date, their reason, and what they replaced. Nothing is erased.
How your AI agents improve
Every plugged-in AI agent logs the history of its actions, and the lessons it has learned.
Your Kastel is versioned text files. That is what makes full export possible: your content is locked into no proprietary format - it is natively OKF-compliant (Open Knowledge Format), the open standard published by Google.
How it gets built
The engine reads what already exists
It derives a first org chart, the real departments, the entities that keep coming up. Before the first question is even asked.
A short interview
The organisation, the key processes, who decides what. The engine never asks again for something already present in your sources.
You validate
The engine proposes an org chart and a responsibility matrix. You correct it, you settle the ambiguous cases, you approve.
What the engine needs to knowExample
Sourcesand the rest
How many departments?6 → 5correctedDrive · org-chart.xlsx
Who runs sales?Camille FabreGmail · 412 threads
How many active customers?214HubSpot
What is the customer refund window?14 calendar daysDrive · terms.pdf
How is a leave request approved?Manager, then HRNotion · internal guide
+ 9 more questions answered by your sources
Who can make an exception to the 14-day window?Head of Sales, above €500your callyou
Which decisions go up to the leadership team?Any commitment above €20kyour callyou
Who is allowed to see HR files?HR and leadershipyour callyou
17 questions to represent your company
Your Kastel takes shape in one session.
With no data team and no weeks of mapping. The actual duration depends heavily on the size and complexity of your company: it is what the product aims for, not an average measured across dozens of deployments.
Each AI has its own access.
A plugged-in AI reads only its perimeter. You cut its access in one click, and the others keep working.
Plugged-in AIPlugged in byIt readsAccess
Quotes agent
Claude Cowork
Camille Fabre
Head of Sales
Head of Sales
SalesOperations
Plugged inread 2 min ago
Dunning agent
Mistral
Marc Lenoir
CFO
CFO
FinanceSales
Plugged inread Monday 08:00
Stock agent
Local model
Inès Roux
Workshop Manager
Workshop Manager
Operations
Plugged inread 40s ago
Executive assistant
GPT
Paul Vidal
CEO
CEO
The whole company
Plugged inread yesterday 18:12
audit chainNo access cut today.4 AIs keep working.
What an AI learns while working becomes a proposal. It never writes into your Kastel itself: a manager approves, corrects or refuses.
How AIs plug into it
Kastel runs no model. It publishes your context, and the AIs come and work on it.
Quotes agent only reads Sales and Operations.
Quotes agent, on Claude Cowork, only reads Sales and Operations. It doesn’t read Marketing, Finance, Customer support, HR.
MCP, the standard socket
MCP is the standard that connects an AI to an organisation’s tools and data. Kastel is an MCP server: that is how your AIs reach your company’s context.
Your own AI keys
Your Kastel runs on your own AI, at the provider you already use or on a model running at your place. Kastel never resells AI and takes no margin on it. And your console shows you what your AIs cost you.
How your Kastel grows
AI proposes, your team decides.
Refunds
1
Refund window: 14 calendar days.
2
Above €500, the exception goes through the Sales Director.
audit chain
What an AI learns does not die with its session. It leaves it in your Kastel, and the next AI starts from what you approved, whichever vendor it comes from.
Kastel in action
A 120-person industrial company in precision engineering.
It connects an AI key and drops in its key documents.
The owner
Sits through the scoping interview. The engine has already pre-filled whatever the documents said and proposes an org chart and a responsibility matrix. Approves, corrects, settles the ambiguous cases.
The methods manager
A month later, plugs in the AI of their choice and asks: “what is our qualification procedure for a new supplier on a critical part?” The AI answers correctly, because it reads the company’s real process, and only what its scope allows it to see.
The quality manager
Approves the changes an agent proposes on a supplier record, down to the exact effect. Everything is recorded.
Nobody had to learn a concept. The owner approved an org chart, the quality manager approved a change.
Your Kastel belongs to you
Your data, your context, your infrastructure
Kastel runs on your own server if you want it to, and the complete core is free there.
Full export
One command, and everything comes out: context, governance, audit logs. No proprietary format to crack, they are text files.
Open interface
The protocol AIs plug into, the export format and the connector contract are open and standard.
Hostable in Europe
If you would rather operate nothing, we host and run a dedicated server for your company, in Europe.
Let’s build your fortress.
Would you rather have help? Our partner integrators take care of it.