For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Dashboard
User GuideDeveloper GuidesAPI Reference
User GuideDeveloper GuidesAPI Reference
  • Getting Started
    • What is Runtype?
    • Creating your account
    • Platform Keys vs. BYOK
    • Understanding the Runtype UI
    • Quickstart: Social Media Post Generator
    • Quickstart: From Agent to Chat Widget
  • Dashboard
    • What is the Dashboard?
    • Daily Executions
  • Playground
    • What is the Playground?
  • Products & Surfaces
    • What are Products?
    • What are Surfaces?
    • Creating a Product
    • Setting up a Chat Surface
    • Setting up an API Surface
    • Setting up an MCP Surface
    • Setting up an A2A Surface
    • Setting up a Slack Surface
    • MCP authentication
    • Authenticating with product API keys
    • Embedding the chat widget (script tag)
    • Embedding the chat widget (React)
    • Surface orchestration modes
    • Product views
    • Adding Capabilities to a product
    • Connecting external agents
    • How A2A works
    • Connecting to Cursor / VS Code
    • Connecting to Claude Desktop
    • Scoping API keys to capabilities
    • Auto-generated OpenAPI spec
    • Calling your API endpoints
    • Client tokens and domain restrictions
    • AI-powered theme generation
    • Widget theming and customization
    • Product versioning and status
  • Flows
    • What are Flows?
    • Creating and Editing Flows
    • Flow step types overview
    • Agent and Flow Templates
    • Using prompt steps
    • Using transform-data steps
    • Using conditional steps
    • Using fetch-url and api-call steps
    • Using record steps (upsert/retrieve)
    • Flow variables and templates
    • Flow versioning and publishing
    • Running flows in batch
    • Handling batch failures
    • Debugging flows
  • Agents
    • What are Agents?
    • Creating and configuring Agents
    • Agent tools
  • Records
    • What are Records?
    • Creating and managing records
    • Using records in flows
    • Filtering and searching records
  • Tools
    • What are Tools?
    • Built-in Tools
    • Creating custom tools
    • Creating external tools
    • Runtime tools
  • Evals
    • What are Evals?
    • Running an Eval
    • Interpreting eval results
  • Schedules
    • What are Schedules?
    • Automating batch processing
  • Logs
    • What are Logs?
    • Working with Logs
  • Integrations
    • Connecting AI model providers
    • Slack integration
    • Google Workspace integration
    • GitHub integration
    • Linear integration
    • Weaviate (vector search)
    • Firecrawl (web scraping)
    • Exa (web search)
  • Settings
    • What's in Settings?
    • Available AI models
    • What are Organizations?
    • Managing AI models
    • Managing API keys
    • Billing and plans
    • Usage data
    • Team members and permissions
    • Appearance and preferences
    • Integrations (PostHog, Weaviate, Daytona)
  • Troubleshooting & FAQ
    • FAQ
    • Rate Limits and Usage
    • Managing Runtype with Claude
    • Flow execution failures
    • Common errors and solutions
    • Authentication issues
Dashboard
LogoLogo
On this page
  • Available modes
  • Single Orchestrator
  • Multi-Capability Router
  • A2A Orchestration
  • Configuring orchestration
  • Orchestration by Surface type
  • Next steps
Products & Surfaces

Surface orchestration modes

Was this page helpful?
Previous

Product views

Next
Built with

Orchestration modes determine how Surfaces route user requests to Capabilities.

Available modes

Single Orchestrator

One Capability handles all incoming requests. The Surface acts as a direct channel to a single Flow or Agent.

How it works: All requests are routed to the selected Capability. This is the default mode and works well when your Product has one Capability or when each Surface is dedicated to a single purpose.

Use when:

  • You have one primary Capability per Surface
  • You want deterministic routing with no AI-based selection
  • The calling application knows which Capability it needs

Multi-Capability Router

An AI model reads each incoming request and routes it to the most appropriate Capability. Users do not need to know which Capability to call.

How it works: A router model evaluates each request and selects the best Capability based on the request content and the Capability descriptions. You can choose the router model and optionally add a custom routing prompt.

Example (chat Surface): User types “Where’s my order?” The router recognizes this as an order status query and routes to the order lookup Agent, not the FAQ Flow.

Use when:

  • Users interact in natural language (chat)
  • You want intelligent request routing
  • Multiple Capabilities handle overlapping domains

A2A Orchestration

A2A Surfaces have their own orchestration model:

  • Delegate mode — Each Capability is exposed as a separate skill in the Agent Card. The calling Agent chooses which skill to invoke.
  • Managed mode — Runtype adds an orchestrator that routes incoming requests to the right Capability. A single managed skill coordinates all visible skills behind the scenes.

Configuring orchestration

Set orchestration mode when creating or editing a Surface:

  1. Open your Product
  2. Select or add a Surface
  3. Go to the Orchestration tab
  4. Select:
    • Single Orchestrator — Direct routing to one Capability
    • Multi-Capability Router — AI-powered routing (choose the router model and optional routing prompt)
  5. Click Save

Orchestration by Surface type

Default and recommended modes vary by Surface:

Surface TypeDefault ModeCommon Use Case
ChatSingle OrchestratorSingle-purpose assistants
APISingle OrchestratorExplicit endpoint calls
MCPSingle OrchestratorTool-based invocation
A2ADelegateAgent skill management

Chat Surfaces: Single Orchestrator is the default. Switch to Multi-Capability Router when you want the Product to route each message to the best Capability among several options.

A2A Surfaces: Delegate is the default. Use Managed mode when you want Runtype to coordinate the Agent’s skills instead of letting the calling Agent pick.

Next steps

  • Setting up a chat Surface
  • Setting up an API Surface
  • Adding Capabilities to a Product