Introduction
Welcome to the Taimoe AI Platform User Guide.
This user guide walks you through the core administrative and developer capabilities of Aegis Console — empowering your organization to securely provision, govern, rate-limit, and monitor Large Language Model (LLM) access across multi-cloud environments.
Console Overview
The Aegis Console interface consists of three primary zones:
- Sidebar Navigation: Located on the left, providing one-click access to Gateway management, Agent Workspaces, Governance policies, and Observability dashboards.
- Top Bar Header: Displays your active Organization and Team scope selectors, user profile settings, and theme toggle.
- Main Content Canvas: Displays interactive data tables, configuration wizards, metrics charts, and diagnostic detail views.
Core Feature Sections
AI Gateway
The core traffic governance engine for routing, throttling, and masking LLM access.
- Virtual Keys: Issue and manage proxy API keys with per-key RPM limits, retry policies, and scope isolation.
- Providers: Connect and store upstream cloud credentials (Google Cloud Vertex AI, AWS Bedrock, Azure OpenAI, OpenAI Direct).
- Models: Register model aliases to hot-swap upstream models and providers with zero client code changes.
Agent Workspace
Build, deploy, and connect intelligent agents to enterprise knowledge and external services.
- Agents: Manage agent configurations, system prompts, knowledge bindings, and test in the interactive Playground.
- Runtimes: Register and monitor container execution environments (Google ADK, Agent Engine).
- Knowledge Base: Connect enterprise vector stores (Vertex AI Search) for RAG grounding.
- Connectors: Integrate external enterprise SaaS tools and data sources (SharePoint, MS Teams).
Governance & Security
Enterprise-grade identity, access controls, and immutable audit logs.
- Identity & Access Management (IAM): Role-based access control (RBAC), team membership, and virtual key permissions.
- Audit Logs: Comprehensive immutable logs tracking every management action and API request payload.
Monitoring & Telemetry
Fleet-wide performance metrics, latency distribution, and step-by-step reasoning traces.
- Observability: High-level dashboards for token budgets, request throughput, and rate limit blocks.
Administration
- Workspace Settings: Organization management, domain security, and Single Sign-On (SSO) configuration.
Ready to get started? Continue to Login & Workspace Setup.