Skip to Content
PlatformTechnical Walkthrough

Technical Walkthrough

This page is for technical readers who want the operating model without jumping straight into implementation details.

Runtime Map

The platform is split into distinct runtime surfaces:

RuntimePortResponsibility
Gateway API8002Provider-compatible proxy, governance chain, health, runner admin routes
B2B API8001Dashboard/admin API for authenticated product operations
Dashboard3001Operator console for keys, logs, costs, approvals, health, and runners
Docs3003Developer documentation site

The Core Flow

Client SDK / app -> Gateway -> Auth + scopes -> Provider resolution -> Governance chain -> Upstream provider call -> Usage recording -> Dashboard, billing, and monitoring surfaces

Gateway Request Path

The gateway is designed to accept provider-style requests while adding organization-aware governance.

Main stages

  1. Authenticate Curate-Me gateway key.
  2. Resolve org and key context.
  3. Enforce scopes such as gateway:write.
  4. Parse request body and requested model.
  5. Resolve provider and concrete upstream model.
  6. Resolve provider credentials from headers, stored secrets, or environment fallback.
  7. Run governance checks.
  8. Proxy the request.
  9. Record cost and usage.

Governance checks

The exact implementation evolves, but the mental model stays stable:

  • plan enforcement
  • rate limiting
  • cost and budget checks
  • PII or secret scanning
  • model allowlists
  • HITL approval gating

Managed Runners

The runner system exists for work that needs an execution environment rather than a single model response.

Examples:

  • browser automation
  • file manipulation
  • shell commands
  • scheduled workflows
  • multi-step agent jobs with persistent state

Runner operating model

Dashboard / API -> Runner control plane -> Template / policy / credentials resolution -> Provider or host allocation -> Session execution -> Files, logs, activity, cost, and lifecycle events

Important runner concepts

ConceptPurpose
TemplatesReusable runner configurations for repeated jobs
Tool profilesLimit what a runner can access
FleetGrouped runner inventory and activity
Your MachinesConnect your own hardware (laptop, server, or VM) to the control plane
Cloud deployOne-click managed provisioning on platform infrastructure
Intent routerConvert natural-language job intent into template-backed execution

Dashboard Data Model

The dashboard consumes two broad categories of backend surfaces:

SourceTypical usage
B2B APIauth, org settings, billing, dashboard widgets, admin actions
Gateway APIpublic health, provider health, gateway-specific operations, runner admin routes

In practice that means the dashboard is not just a thin shell over one API. It bridges both the admin plane and the gateway plane.

Health, Logs, And Cost Flow

Gateway request -> response completes -> usage record created -> Redis accumulators updated -> MongoDB usage/audit persisted -> dashboard log viewer and billing sync consume the resulting data

What this enables:

  • request-level logs
  • cost rollups
  • budget enforcement
  • provider health views
  • operator investigation after incidents

Audience-Specific Reading Paths

Where To Go Next