--- title: "What do Wireflow terms like node, workflow, blueprint, credit and run mean?" description: "A node is one piece of a workflow, a workflow is the board you build and run, a blueprint is a frozen copy, credits pay for runs, and a run is one execution." updated: 2026-10-29 --- In Wireflow, a node is one piece of a workflow, like an AI model; a workflow is the board where you build and run work; a blueprint is a frozen copy of a workflow; credits are how you pay for AI runs; and a run is one execution of a workflow. All eleven terms are in the table below, and each one has its own section with a link to the page that explains it. | Term | What it means in Wireflow | | --- | --- | | Node | One piece of a workflow, such as an AI model or a Text Input | | Workflow | The board where you build and run work | | Blueprint | A frozen copy of a workflow that other boards fork or add as a single node | | Playbook | A workflow tagged `playbook` whose document nodes hold your team's rules | | Template | A published workflow from the community library that you copy and edit | | App | A workflow you publish so others can run it on a web page or over the API | | Credit | What you spend on AI runs, priced by the model and its settings | | Run | One execution of a workflow, which charges for the paid nodes that run | | Iterator | A node that fans a workflow out over a list inside one run | | Connector | The MCP endpoint that lets an AI agent build, inspect and run your workflows | | Skill | A ready-made job for your AI agent, such as a product clip or a set of ad images | New to Wireflow? [Getting Started](/docs/getting-started) walks you through opening a new workflow, adding a model node and running it, and the account docs cover [credits, limits and recent changes](/docs/account). ## What is a node in Wireflow? A node is one piece of a workflow, such as an AI model or a Text Input, that you add to the canvas and connect to other nodes. Paid nodes, such as image and video models, bill credits and never run by themselves, while free nodes recompute locally and cost nothing. [All Nodes](/docs/nodes) lists every node with its inputs, settings and credit cost. ## What is a workflow in Wireflow? A workflow is the board where you build and run work: the nodes, the wires between them and their outputs. One made in your personal workspace is private until you share it, and one made in a team workspace belongs to that team. [Creating Workflows](/docs/creating-workflows) covers the editor in full. ## What is a blueprint in Wireflow? A blueprint is a frozen copy of a workflow that other boards fork or add as a single node, and later edits to the source board do not change it until someone republishes it. Forking copies it into your account as a new workflow you can edit, while adding it puts it into a workflow you own as one [Blueprint node](/docs/nodes/blueprint--invoke). Publishing a blueprint is limited to Wireflow admins today, and [Workflows, Blueprints, Folders and Playbooks](/docs/workflows-blueprints-playbooks) compares it with workflows, project folders and playbooks. ## What is a playbook in Wireflow? A playbook, or team playbook, is a normal workflow tagged `playbook` whose document nodes hold your team's rules, next to example outputs that show what good looks like. Agents read it with the `get_project_context` MCP tool, so they follow your rules without being told each time. Keeping it in a folder in your team workspace is what makes it the team's playbook, and tags are set through the API today. [Team Playbook and Project Folders](/docs/project-context) explains how agents read it. ## What is a template in Wireflow? A template is a published workflow from the Wireflow community library that you can copy into your account as an editable workflow. Copying is free, editing your copy leaves the original unchanged, and running the copy uses credits like any other workflow. [Templates](/docs/templates) shows how to find and copy one. ## What is an app in Wireflow? An app is a workflow you publish so other people can run it, on its own web page with a form or over the API by its slug. Over the API, each caller starts it with `POST /api/v1/apps/{slug}/execute` and their own key with the `apps:execute` scope, and the key owner's credits pay for every node in the run, not the app creator's. [Publishing Apps](/docs/publishing-apps) covers the app's web page, sign-in and subscriptions, and [let others run your workflow](/docs/publish-a-workflow-as-an-api-endpoint) covers the API side. ## What is a credit in Wireflow? Credits are how you pay for AI runs in Wireflow: each model node that runs costs credits based on the model and its settings. You pay for the nodes that run, so if a run stops early, the nodes that already finished are still charged. Your balance is shown in the top navigation bar, [Credits & Billing](/docs/credits-and-billing) covers what models cost per run and how to buy credits, and the [pricing page](https://www.wireflow.ai/pricing) shows what each plan includes. ## What is a run in Wireflow? A run is one execution of a workflow, and it charges credits for the paid nodes that run. You can start one in the editor, from your code with `POST /api/v1/workflows/{id}/run` on a workflow you own, or from an agent with the `run_workflow` tool. Code gets back an `executionId` to poll, and an agent polls the run with `get_execution` for its status and output URLs. For the API details, see [Run Workflows](/docs/api/run). ## What is an iterator in Wireflow? An iterator is a node that makes a workflow fan out over a list inside one run: the [Text Iterator node](/docs/nodes/iterator--text) iterates over a list of text values, and the [Image Iterator node](/docs/nodes/iterator--image) over a list of images with timestamps. The run's outputs hold one entry per take, each with its `iteration` number. A node's credit estimate covers one run of that node, so multiply it by the number of items yourself. [Run one workflow over a list](/docs/workflows/run-over-a-list) shows how to wire it. ## What is a connector in Wireflow? A connector is how an AI agent such as Claude reaches Wireflow: Wireflow speaks the Model Context Protocol (MCP), so any MCP client can build, inspect and run your workflows for you. You add `https://www.wireflow.ai/api/mcp` as a custom connector in your MCP client, and the client walks you through Wireflow's OAuth sign-in and a consent screen, with no API key to copy. The separate [Editor Connector](/docs/mcp/editor) at `https://www.wireflow.ai/api/mcp/editor` lets an agent edit video timelines and render media already in your account, and it generates nothing. The [MCP connector page](/docs/mcp) lists each tool with the permissions it needs, and [Use Wireflow from your agent](/docs/use-wireflow-from-your-agent) has the connection steps for every client, including ChatGPT. ## What is a skill in Wireflow? A skill is a ready-made job for your AI agent, such as a product clip or a set of ad images. In Claude Code, a skill is a folder with a `SKILL.md` file of instructions that Claude uses when your request matches it, or when you call it by name as a slash command. Wireflow's public skills plan the job in Claude, show the credit cost and your balance, and run a published Wireflow app through the MCP connector only after your yes. [Claude Code Skills](/docs/skill) lists every skill and covers the builder skill, which uses an API key so Claude can build, update and run your own workflows. Last updated: 2026-10-29 --- Documentation index: fetch https://www.wireflow.ai/llms.txt for the full list of Wireflow docs.