AI operations and governance
Enterprise
Production AI needs an operating model, not only a provider key. Kumiko Enterprise keeps the controls close to the tenant, policy, handler, and audit boundaries of the application.
The operating loop
Section titled “The operating loop”- Configure a provider and its secret for the tenant.
- Define the prompt and step defaults in code.
- Tune tenant policy or prompt revisions without changing the pipeline structure.
- Evaluate with mock responses and golden fixtures before activation.
- Activate or roll back the revision explicitly.
- Inspect each model call with its tokens and cost on the ai-foundation AI calls screen.
- Review executed writes in the normal audit path.
The main controls
Section titled “The main controls”| Control | Where to start |
|---|---|
| Provider and model selection | ai-foundation and provider reference |
| Prompt history and rollback | prompt-store |
| Draft, activate, and rollback | ai-pipeline |
| Token, transcription and read-aloud budgets | The Assistant and cap-counter |
| Step policy and cost | Cost control |
| Launch evidence | Production AI governance |
What to persist
Section titled “What to persist”A step’s output is application data. It needs the application’s data classification before it is persisted or logged.
Assistant conversations and tool calls are application data. Apply the same field access, retention, export, erasure, secret handling, and backup rules as for other tenant and user data.
Build your own operations layer
Section titled “Build your own operations layer”You can implement a smaller policy entity, evaluation runner, or audit report with public Kumiko features. Enterprise packages the revision model, activation commands, golden fixtures, dry runs, and caps so teams do not have to assemble those controls repeatedly.