Core Services

Core Services in the Admin UI sidebar groups AI Gateway, access control, governance, and FinOps pages above Model training.

Use this section when you need to connect providers, onboard users, enforce policies, attach MCP tools, or monitor cost and reliability.

Next: if the organization is new, start with First Steps. Otherwise follow Setup → Govern → Monitor and optimize, or jump from the menu section overview. For AIOps pages, see Model Training.

Setup

1. Providers — Connect vendor endpoints, enable models, set per-provider limits, and define routing rules and fallbacks.
2. AI Access — Invite users, set spend and quota limits, choose allowed providers, and enable context compression.
3. MCP Servers — Register optional Model Context Protocol integrations so Chat and agents can call external tools.

Govern

1. Policies & Guardrails — Enforce safety, compliance, and content controls on Chat and API traffic.

Monitor and optimize

1. Home → Dashboards — Check cost, volume, reliability, guardrail, and cache trends at a glance.
2. Optimizations — Compare would-have-paid vs actual spend and measure savings by technique.
3. Analytics → Usage and Cost — Drill into consumption, spend, and activity by model, user, team, or agent.
4. Analytics → Traces — Inspect individual requests for latency, routing, tokens, cost, and payloads.

Menu section overview

Table 1: OptScale AI Core Services — sidebar menu items

Menu item	Purpose
Home / Dashboards	At-a-glance operational health for cost, volume, reliability, and cache efficiency.
AI Access	Onboard members; manage limits, teams, allowed providers, and compression.
Providers	Connect AI vendors, enable models, set quotas, and configure routing.
Policies & Guardrails	Define reusable guardrails and attach them to evaluation policies.
MCP Servers	Register MCP servers and control which tools are enabled or auto-run.
Optimizations	Measure projected and realized AI cost savings from optimization features.
Usage and Cost	Under Analytics — FinOps views for tokens, spend, and scoped activity.
Traces	Under Analytics — Per-request audit and debugging for AI traffic.

See also

• Architecture Overview — Platform structure and request flow.
• Experiment Tracking — Tasks, models, datasets, and artifacts.
• Environments & Operations — Shared runtimes, cloud connections, and power schedules.
• Interface Overview — Chat workspace for end users.