Tenant and workspace isolation
Each workspace is separated so agents only operate inside the environment they are assigned to.
Trust Layer
Duka Agents should not roam raw enterprise systems
Duka protects organizations by giving agents access to governed knowledge objects instead of raw operational systems, inboxes, folders, social accounts, or admin tools.
The safer pattern: expose only the knowledge needed
Instead of connecting an agent directly to everything, Duka first processes information into controlled objects with ownership, access rules, citations, lineage, freshness, quality status, and allowed actions.
Role-based access
Users receive answers based on permissions, workspace role, and allowed knowledge objects.
Citation-aware retrieval
Answers can point back to files, records, conversations, or source summaries used as evidence.
Freshness and quality checks
Agents can surface when knowledge is current, stale, incomplete, or not strong enough to answer safely.
Allowed actions
Skills constrain what an agent is approved to retrieve, draft, route, or execute.
Audit context
Sensitive retrieval and task execution can retain traceability across users, sources, and workflows.
Deployment choices for different governance models
Duka can be delivered as managed SaaS for speed, or as a dedicated instance when policy requires stronger isolation, customer-specific deployment boundaries, or private integration controls.
Least-privilege access
Encryption in transit and at rest
Environment separation
Secrets management
Backup and recovery controls
Monitoring and incident workflows
No answer without access and evidence
If a user is not allowed to access a source, the agent should not use it. If evidence is missing or stale, the agent can fall back safely instead of inventing an answer.
Safe skills for real work
Duka Agents can retrieve, explain, summarize, draft, and route tasks only through approved knowledge objects and controlled workflows.