01 · Work
Start with an everyday task
Draft a general email, summarise permitted text or brainstorm an idea. Use the company’s approved model connection from one workspace.
Cloud workspace · pilot discussions
An AI workspace for the work in front of you.
Draft a first version, make a summary clearer or explore a new idea. Your company’s configured policy is applied within the conversation, before requests reach an approved external model.
Kubrius workspaceInteractive example
AssistantApproved connection
You
Draft a friendly invitation to our public webinar.
Permitted by the example policy
Illustrative response
Join us for a practical conversation about making AI useful at work. Bring your questions — we’d love to hear them.
What would you like to work on?
Part of the work
Write a request. The controls travel with it.
Your team asks for help in the workspace. Kubrius checks the outgoing request and included conversation history before a configured model is called.
02 · Check
Apply company rules automatically
Supported identifiers are masked; detected restricted content is held. Staff receive an explanation when a request cannot continue.
03 · Understand
See the decision and the usage
Review the outcome, the policy version that applied and usage evidence. These controls cover requests made through Kubrius.
Detection uses a limited set of patterns. It can miss sensitive information, so permitted tasks and data must be agreed before a pilot.
Inside the workspace
Everyday help. Understandable decisions.
Illustrative policy examples, not generated answers or a live model connection.
“Draft a friendly invitation to our public webinar.”
Decision
Allowed by the example policy
Next
With a live connection configured, the request goes to the approved external model.
Your part
Review and edit the draft before using it.
“Rewrite this invitation for [email protected].”
Before call
The email address is replaced with a request-specific placeholder.
On return
Supported placeholders are restored in the answer.
Boundary
The remaining text goes to the model provider. Masking is not complete anonymisation.
“Summarise this confidential client contract.”
Decision
Held by the example policy
Next
The request is stopped before a model call. The workspace explains the restriction.
Boundary
It is not rerouted to Core. Automatic private routing is not connected in the cloud workspace.
For the business
Know the rules. Understand the use.
Access
A company workspace
Organisation-scoped accounts and administrator/staff roles. Pilot accounts are provisioned with you.
Policy
Rules with a history
Versionable policy configuration and stored decision snapshots show which rules applied to a request.
Usage
Defined allowances
Monthly allowance reservations and daily request limits help bound model use through the workspace. Actual provider billing is verified during setup.
Where we are today
See the controls. Scope a pilot.
Core runs the workspace locally with a private model, an API and agentic workflows. The cloud workspace has a working demo with simulated responses; live cloud pilots depend on completing the model connection and operational setup.
Ready to demonstrate
Workspace and controls
Sign-in, company roles, supported identifier masking, policy decisions, version history and usage limits are implemented in the pilot foundation.
Before a live pilot
Agree and verify the setup
Confirm the model provider, data handling, hosting, retention, permitted tasks and usage allowance. Live deployment and provider billing still need validation.
Cloud pilot boundaries
Separate from Core
Company-document Q&A is deferred in the cloud workspace. Core’s local model, API and workflow execution are a separate deployment; automatic cloud-to-Core routing is not connected.
Good questions
Clear expectations.
Does cloud AI keep everything on our premises?
No. Allowed cloud requests are processed by an external model provider after the workspace checks. Supported identifier masking does not make the whole request anonymous. Provider location, retention and training terms must be agreed for the selected connection; UK application hosting alone would not establish UK model processing.
Do employees have to run a separate policy check?
No. Checks are integrated into the request flow. Employees write in the workspace; Kubrius applies the configured rules before calling the approved model.
Can you detect every confidential detail?
No. Current controls recognise supported email addresses, UK mobile numbers and National Insurance numbers, plus some secret and restricted-content patterns. They can miss names, indirect identifiers and confidential context. Use only the data and tasks agreed for your pilot.
Do we need Core to get started?
No appliance is required for a cloud workspace pilot. Core runs the workspace locally with a private model, an API for existing tools and agents, and agentic workflow execution. Automatic routing from the cloud workspace to Core is not yet connected.
Start with one useful task
See how Kubrius could work for your team.
Arrange a walkthrough with Chris, or discuss a small cloud pilot. Bring an everyday task and the rules your business needs to apply. We’ll agree the scope, setup and usage before any pilot starts.
- A relaxed 15 minutes, directly with the founder
- See the workspace and discuss your first use case
- I'll reply personally. No spam, no drip funnel
Thank you.
Your message has been received. Chris will get back to you personally to arrange a time.