Vuva AI

Internal · Editorial operations

AI Content Operations Dashboard

Demo workspace — simulated telemetry, real workflows

AI governance

These controls are implemented in this repository’s services — each names the enforcing code. This dashboard makes governance inspectable, not just documented.

Human approval required

ENFORCED

Where: WorkflowService.transition() — publication requires prior approval by a human actor; the orchestrator identity is rejected.

No AI output reaches readers without an accountable person signing the exact revision.

Provenance labelling

ENFORCED

Where: DraftRecord.aiLabelVisible persists through every workflow state; the label is rendered wherever a draft appears.

Readers and reviewers can always tell AI-assisted material from purely human work.

Source attribution

ENFORCED

Where: RagService post-validates citations against retrieval results; answers display their exact source passages.

Every generated claim can be checked against the content it came from.

Prompt-injection defence

LAYERED

Where: scanForInjection on inputs and retrieved text; delimitUntrustedContext wraps sources; TRUST_BOUNDARY_PREAMBLE in every system prompt; outputs schema-validated.

Retrieved documents are data, never instructions — attempts to hijack generation fail closed.

Evaluation gates

ADVISORY

Where: Seven-dimension harness runs before review; low grounding or a safety FAIL flags the draft for scrutiny.

Machines catch the mechanical failure classes so humans can spend attention on judgement.

Privacy & data minimisation

ENFORCED

Where: No visitor tracking; declared profiles only; provider calls carry task text, never user identifiers; audit meta hashes long inputs.

The platform demonstrates that personalization does not require surveillance.

Auditability

ENFORCED

Where: Append-only event log for generations, edits, evaluations, approvals, publications and config changes — visible in the Audit Log panel.

Any editorial decision can be reconstructed later: who, what, when, which revision.

Controlled AI usage scope

ENFORCED

Where: The assistant exposes nine whitelisted operations; anything outside them (publishing, approving, altering governed quotes) has no code path.

Governance by construction beats governance by policy document.

Demonstrating injection defence

The RAG panel includes a live probe — send instruction-style text at the endpoint and observe the guardrail refuse it.

Part of the Vuva Systems portfolio — vuvasystems.com