Skip to main content
This is the fastest way to see ModuleX work end to end. You will create a workflow in the workflow builder, run it, and watch each step report its result live — all without writing code or touching the API. You have two ways to build, and you can mix them:

Describe it to the AI Composer

Type what you want in plain English. The AI Composer generates an editable workflow on the canvas for you.

Build it by hand on the canvas

Drag nodes onto the canvas and connect them yourself. Full control, no AI.

​
Before you start

1

Sign in to the ModuleX app

Open the app and sign in. If this is your first time, create an account and an organization — every workflow belongs to an organization.
2

Open the workflow builder

Go to the workflow builder. If you have no workflows yet, you will see an empty state with a Create your first workflow button.
Building and running workflows in the app requires an owner or admin role in your organization. If you do not have it, ask an organization owner to grant access. See organizations, roles & membership.

​
Option A — Describe it to the Composer

The AI Composer turns a plain-English description into a real, editable workflow on the canvas. It is the quickest way to get a working draft.
1

Create a workflow and open the Composer

From the builder, create a new workflow. The right-hand panel includes a Chat tab — this is the Composer.
2

Describe what you want

Type a request in your own words, for example:
Example Composer prompt
The Composer streams its work back to you: you will see it plan, add nodes, connect them, and explain what it changed.
3

Answer any questions it asks

The Composer may pause to ask you something — for example, which option to use or to connect a credential for an integration like Slack. Answer in the chat and it continues. This pause-and-ask behavior is human-in-the-loop; the Composer waits for your reply before moving on.
4

Keep or undo the changes

When the Composer finishes, its edits appear on the canvas as pending changes. Use Save to keep them or Revert to roll back to the previous version. Nothing is permanent until you save.
The Composer edits a real workflow graph, not a throwaway preview. After it finishes you can keep refining by hand on the canvas, or ask it for more changes in the same chat. For a longer, guided build, see build a workflow with Composer.

​
Option B — Build it by hand on the canvas

Prefer to drive it yourself? Build directly on the canvas.
1

Add nodes

Drag nodes from the node dock onto the canvas. Each node is one step. Common starting points:

LLM node

Call a language model with a prompt to draft, summarize, or classify text.

Tool node

Call an integration action, such as sending a Slack message or creating a record.

Knowledge node

Retrieve relevant context from a knowledge base.

Conditional node

Branch the flow or loop over a list of items.
2

Connect the steps

Draw an edge from the start marker into your first node, then connect each node to the next. The start marker is added for you — you connect your steps to it. Every node passes its result forward so later steps can use it.
3

Configure each node

Select a node to open the detail panel and fill in its settings — the prompt for an LLM node, the action and inputs for a tool node, and so on. If a node needs a connected account, the builder flags it so you can connect a credential before running.
The canvas validates as you build. It will flag a node that has no path from the start marker, a node that is missing a required credential, or a knowledge node with no query — so you can fix issues before you run.

​
Run it and watch the stream

When your workflow is ready, run it from the builder and watch each step report back in real time.
1

Click Run

Select Run. If your workflow takes input, enter the values it asks for first. The builder runs the workflow exactly as it appears on your canvas — you do not need to deploy it first to test it.
2

Watch the live stream

Each node moves through pending → running → completed as the run progresses, and its output appears as it finishes. Behind the scenes this is a live event stream, so you see results arrive step by step rather than waiting for the whole run to end.
3

Respond if the workflow pauses

If your workflow includes an interrupt node, the run pauses and asks you a question. Answer it and the run continues from where it stopped — it stays the same run.
4

Inspect the result

When the run finishes, open the node outputs to see what each step produced. The Runs panel keeps a history of past runs so you can revisit any of them.

​
What if a run is blocked?

Some steps use ModuleX-managed models and storage, which are metered in credits. If your organization has run out of its plan allowance and has no wallet balance to cover the overage, a run can be refused before it starts — you will see a billing message instead of a run, and nothing is charged. To fix it, top up or upgrade. Learn how this works in usage gating & limits.
Using your own provider keys (BYOK) is not metered in credits. Managed models and managed knowledge are. See credits & the billing model for what consumes credits.

​
Next steps

Tour the workflow builder

Learn the canvas, nodes, and controls in depth.

Build with the Composer

A full walkthrough from prompt to running workflow.

Run a workflow from chat

Trigger and watch a run directly inside a chat.

Run a workflow from code

Do the same thing programmatically with cURL, Python, or JavaScript.