Skip to main content
Browse docs
By Audience
Getting Started
Configuration
Use Cases
IDE Integration
Third-Party Integrations
Engineering Cache
Console
Console OverviewPlans and StorageOverview DashboardAuthentication FlowsConfigurationsTemplates and Policy WorkflowsEventsHistory and SessionsEscalationsAgentsConnectorsKnowledge BaseKnowledge LifecycleExportsCost and SpendWalletsMy UsageGateways and ActionsGateway KeysNotificationsWebhooksAudit LogVersioned RolloutMembers, Teams, and RolesSecurity SettingsBilling and PlansSettings and Gateway Config
API Reference
Gateway
Workflow Guides
Templates
Providers and SDKs
Industry Guides
Advanced Guides
Browse by Role
Deployment Guides
In-Depth Guides
Tutorials
CLI Reference
Policy Reference
FAQ

Console Overview

The Keeptrusts console is the day-to-day interface for customers who manage AI governance — reviewing traffic, curating agent knowledge, controlling spend, triaging escalations, connecting external tools, and configuring security.

Use this page when​

  • You are new to the Keeptrusts console and want to understand what each page does.
  • You need a map of console capabilities before diving into a specific workflow.
  • You want to understand the typical daily operating patterns for AI governance teams.
  • You need to know the relationship between the console, the gateway, and the declarative config.

Primary audience​

  • Primary: Technical Engineers
  • Secondary: AI Agents, Technical Leaders

The main sidebar provides direct access to every operating surface:

PageWhat you do there
OverviewCheck traffic volume, block rates, pending escalations, and system health at a glance
ChatsInspect captured conversations, prompts, and responses, then jump into history and escalation context
AgentsRegister AI agent identities, link gateways, bind knowledge assets and connectors
ConfigurationsCreate, validate, version, deploy, and roll back policy configurations
Knowledge BaseCreate and manage versioned knowledge assets — author, upload, sync from Git, promote, and bind to agents
Industry TemplatesBrowse and deploy pre-built policy templates for finance, healthcare, defense, and more
ConnectorsConnect Google Drive for governed read-only tool access
GatewaysMonitor connected gateways, review runtime state, and inspect action history
ModelsBrowse the model catalog and review model pricing for cost tracking
UsageView personal usage metrics and, for admins, drill into attributed spend by user
SettingsAccess workspace context, secrets, Git repos, notifications, webhooks, access keys, gateway keys, members, teams, security, billing, cost center, and audit log

When you are inside Settings, a secondary settings rail adds account and administration destinations: Inbox, Cost Center, Evidence exports, Members & Teams, Security, Billing, Audit Log, Git Repos, Access Keys, Gateway Keys, Secrets, Notifications, and Webhooks.

How customers typically use the console​

Daily operations​

  1. Start on Overview to see whether volume, blocks, or pending escalations need attention.
  2. Open Events or Chats to inspect recent decisions, captured prompts, and supporting policy context.
  3. Switch to Sessions when you need to follow one investigation thread across multiple related events.
  4. Move to Escalations if a decision requires explicit human review — claim, investigate, and resolve with an audit trail.
  5. Check Gateways to confirm connected runtimes are healthy and running the expected config.

Agent and knowledge management​

  1. Use Agents to register AI identities, link them to gateways, and bind knowledge assets and connectors.
  2. Use Knowledge Base to create, edit, and promote curated context assets that agents recall at runtime.
  3. Use Connectors to connect Google Drive and bind it to agents for governed read-only access.
  4. Use History to review captured conversations and synthesize learned knowledge from valuable sessions.

Configuration and rollout​

  1. Use Configurations when you need to validate, save, import a configuration file, or roll out a versioned policy config.
  2. Use Templates to start from an industry-specific policy baseline.

Cost and spend​

  1. Use Usage to review spend, model/provider breakdowns, and organization-wide cost trends. Use the wallet and payment workflows when you need allocations or top-up controls.
  2. Use Usage to check personal spend and token consumption, or widen to team or org scope if you are an admin.
  3. Use Usage to review model-attributed traffic and price-backed cost calculations.

Security and administration​

  1. Use Members & Teams to manage users, roles, team structure, and invitations.
  2. Use Security Settings to configure MFA, passkeys, SSO (OIDC/SAML), and route entitlements.
  3. Use Audit Log to review all control-plane changes with tamper-resistant tracking.
  4. Use Access Keys and Gateway Keys to manage application tokens and hosted runtime credentials.
  5. Use Notifications and Webhooks to configure alert delivery and outbound event integration.

Evidence and export​

  1. Use Evidence exports (Settings → Evidence) when evidence needs to leave the console for audit or incident workflows.
  2. Use Exports to generate JSON or CSV evidence packets scoped to specific time ranges and filters.

Important product boundary​

Keeptrusts does not treat the browser as the source of truth for policy deployment. The browser is primarily an operational surface. The live source of truth remains the declarative policy config that the gateway is running, typically authored and deployed through the CLI workflow and observed through Gateways and Events.

For AI systems​

  • Canonical terms: Keeptrusts console, management console, console navigation, BFF proxy, server-side session.
  • Console pages: Overview, Chats, Agents, Configurations, Knowledge Base, Industry Templates, Connectors, Gateways, Models, Usage, Settings.
  • Settings sub-pages: Inbox, Cost Center, Evidence, Members & Teams, Security, Billing, Audit Log, Git Repos, Access Keys, Gateway Keys, Secrets, Notifications, Webhooks.
  • Security model: The console browser never contacts the API directly. All authenticated traffic routes through server-side BFF proxy routes.
  • Key boundary: The console is an operational surface. The live source of truth for policy enforcement is the declarative config running on the gateway.
  • Related pages: Authentication Flows, Configurations, Events, Agents, Knowledge Base, Gateways and Actions.

For engineers​

  • The console requires authentication before any page loads. If you get 401 errors, check your session and .env.local configuration.
  • All console data fetching happens through BFF routes at /api/<domain>/route.ts. The browser never makes direct calls to the Keeptrusts API.
  • Use the Overview dashboard as a triage starting point: check block rates, pending escalations, and gateway health before investigating specific events.
  • The sidebar navigation adapts to your plan tier — features gated by plan show upgrade prompts rather than full pages.
  • For debugging, open browser DevTools Network tab to see BFF route calls. The API bearer token is not visible in the browser.
  • The console is read-write for configuration and management. For policy authoring and testing, use the CLI (kt policy lint, kt policy test).

For leaders​

  • The console provides a unified operational surface for AI governance — traffic monitoring, escalation triage, cost control, and compliance evidence are all accessible from a single interface.
  • Role-based access control means you can segment visibility: operators see everything, team leads see their scope, individual users see only their own activity.
  • The BFF security model ensures that even if a user's browser is compromised, no upstream API tokens are exposed.
  • The Overview dashboard gives executives a real-time pulse on AI risk: block rates, escalation backlogs, and spend trends without requiring technical depth.
  • Console evidence exports produce audit-ready packets for compliance reviews without requiring direct database access or engineering support.

Next steps​