Sovereign AI in practice
BKS Lab
In BKS Lab we make visible how we make confidential corporate knowledge accessible, automate processes, and let specialized AI agents work together under control. The setups combine delivered solutions, our own tools, and interactive demonstrators.
From a reference project
Automatically presorting incoming mail
Clear-cut requests are filed automatically. Only uncertain cases reach a person.
Drawing continues to the right, scrollable sideways
Classification Reference project · abstracted process in live operation One stop for approval by humans: Approval
Areas of work
What we build and test
Six areas of work show how we make knowledge usable, automate processes, and bring AI systems into operation under control.
Automating processesWe connect inputs, business checks, and target systems into continuous, traceable workflows.
Invoice processing · Inbox · ApprovalsTwo delivered reference workflows · one comparison model
Making operations understandableWe translate operational states into plain-language notifications and provide a controlled channel back for follow-up questions.
Operations monitoring · Plain-language notifications · Reply channelTested in our own operations
open-bridge · Agent contextopen-bridge bundles project knowledge, rules, and tools into a clearly bounded working context for AI agents.
Project context · Safeguards · Open standardsOpen Source · MIT
k2a · Knowledge toolWith k2a we test how knowledge from existing storage locations is checked and made available directly for concrete tasks.
Knowledge access · Verification steps · Multiple storage locationsIn-house development
Making knowledge usableWe make existing document collections usable for search and natural language. Source locations and verification steps stay visible.
Document processing · Knowledge search · Existing storage locationsProduct concept · k2a in closed trial
Orchestrating agentsWe break tasks down into specialized agents and make handoffs, responsibilities, and human decisions visible.
Modular agents · A2A protocol · SimulationStructural diagram · not a specific deployment
See how we approach this under Our approach.
Interactive
Two setups to try yourself
A simulation makes agent handoffs visible. In the A2A chat, you talk to a publicly reachable BKS agent.
- 01 · SimulationStart the agent flow →
Control the pace and stations and watch how tasks pass between specialized modules.
- 02 · Live agentAsk the BKS agent in the A2A chat →
Ask general questions about BKS-Lab and experience standardized communication over the A2A protocol.
Your message is sent to the agent. Please do not enter any confidential information.
The lab overview does not process any input. Only the marked A2A chat sends your message to the BKS agent.
Open Source · MIT
open-bridge: context, rules, and tools for AI agents
open-bridge standardizes how AI agents receive project knowledge, rules, and tools. Instead of starting each task without context, they work inside a clearly bounded environment with traceable responsibilities and safeguards.
We use open-bridge in our own work and develop the framework publicly under the MIT license. It is not tied to a specific AI model or a single interface.
Used in our own operations · Publicly verifiable · Open source
Where does a first, clearly bounded pilot pay off?
Bring a process or a document collection. Together we assess whether sovereign AI provides meaningful support and what a solid starting point could look like.
Schedule a conversation