What is Runtype? | Runtype Documentation

Runtype is an AI product development platform. Use it to build, test, deploy, and monitor AI capabilities in user-facing products.

Who is Runtype for?

If you build an AI-powered experience for a software company, product team, startup, or agency, use Runtype. Move from a working demo to a production-ready product.

To get started, create your Runtype account.

Core capabilities

Use Runtype to build and operate AI capabilities:

Build AI agents and workflows: Create Agents and multi-step Flows with prompts, API calls, transforms, and conditions.
Deploy through Surfaces: Expose your AI capabilities through chat widgets, email, Slack, REST APIs, Model Context Protocol (MCP) Servers, and Agent-to-Agent (A2A) Agents.
Test and compare: Use Evals to compare model and prompt configurations with the same test inputs. Review output, success rate, latency, cost, and token usage.
Monitor and debug: Review execution logs, inspect failures, and improve your workflows.

How Runtype works

Build a Flow or Agent, attach it to a Product as a Capability, and expose it through one or more Surfaces. Use Records for structured context and Tools for actions or external data. Test configurations in Evals or the Playground before you deploy them.

The following table shows how the main platform objects fit together:

Object	Role	Connection
Flow	Runs a repeatable sequence of steps.	Add it to a Product as a Capability.
Agent	Lets a model select tools and sequence calls.	Add it to a Product as a Capability.
Product	Groups related Capabilities.	Add one or more Surfaces.
Surface	Routes requests to a Product’s Capabilities.	Exposes the Product through an interface.

Use these concepts throughout the platform:

Flows: Build repeatable, multi-step workflows when you can define the steps and branches before each run.
Agents: Build workflows in which a model selects tools and sequences calls based on a goal.
Products: Group related Flows and Agents as Capabilities, then deploy them through one or more Surfaces.
Surfaces: Provide deployment channels such as chat widgets, REST APIs, MCP Servers, A2A Agents, Slack, and Email.
Capabilities: Attach Flows or Agents to a Product and expose them through its Surfaces.
Records: Store structured data with JSON metadata so Flows and Agents can use it as context.
Tools: Add actions that Agents and Flows can use to search the web, call APIs, run code, or connect to external services.
Evals: Compare model and prompt configurations with the same test inputs before you change a Flow.

Use the Dashboard to review account activity and open the main product areas. Use the Playground to test prompts, models, settings, and Tools before you save a Flow or Agent.

Example: deploy a support workflow

Alex works on a support team at Example Organization. They create a Flow that drafts responses to customer questions, attach it to a Product as a Capability, and add a REST API Surface. Their application sends requests to the Surface, which routes each request to the Capability. Alex uses Records for support context and Evals to compare model and prompt configurations before deployment.

Platform keys and bring your own key (BYOK)

Start with platform keys to use popular AI models without creating provider accounts or adding provider configuration. To use your own provider credentials, connect AI model providers in Runtype.

You can use platform keys and BYOK at the same time. Use your own keys when you need direct provider billing, dedicated rate limits, or access to more models.

Next steps

Continue with these guides:

Quickstart: Build a Social Media Post Generator as a REST API: build a Flow and expose it through a REST API Surface.
What are Products?: group Capabilities and Surfaces in a Product.
What are Surfaces?: choose a deployment channel for your Product.
Platform keys vs. BYOK: choose how Runtype connects to AI model providers.