🛡 AI Governance Portal

📝

Prompt Registry6 DB-managed system prompts, version history

⚙️

Model GatewayProvider, model selection, toggles

🤖

Agent BuilderDB-stored agent definitions and lifecycle

📊

Eval HistoryNightly eval runs, regression tracking

💰

Cost GovernanceBudget limits, spend tracking, projections

🔌

Connectors8 data sources — health, sync, write-back

🔑

SSO / IdentityOIDC providers, JIT provisioning

👥

Users & RolesRBAC, ABAC, scopes, lockout

✋

HITL ApprovalsPending write-tool approval requests

📈

AnalyticsQuery patterns, latency, error rates

🛡

AI FirewallBlocked requests, injections, jailbreaks

🛒

Agent MarketplaceDiscover, install, clone & publish agents

⚡

Agent RuntimeLive executions, health, versions

🧵

Workflow DesignerVisual LangGraph workflow builder

🕸

Knowledge Graph StudioEntity relationships, data lineage, graph explorer

📋

Model RegistryApproval workflow, security review, cost

🧬

Lineage ExplorerSource index, query provenance, chunk tracing

🛡

AI Policy EngineKeyword blocks, topic gates, model restrictions

🔎

AI ExplainabilityChunk scores, retrieval trace, reranker signals

⚖️

Responsible AI DashboardFairness, bias, violations, dept quality

🛡

Security Review AgentAI code security gate, secret scanning, compliance

🧪

Simulation LabRetrieval config, provider cost & B2B campaign simulation