# Automate a process

Build a workflow as a form or on the Visual canvas, set its trigger, steps, branches, approvals and output, and read it as code or let Copilot propose it.

**Automate a process** builds a workflow: a single trigger, the steps that gather, analyse and generate, branches and approval gates where they are needed, and an output that returns or delivers the result. Members start it from the Work Room or it runs on a schedule or a webhook.

**Who can use it:** the **Builder** role or higher, in a tenant licensed for agents.

Video: Automate a process (3:06), https://katonicdocsmedia.blob.core.windows.net/docs/automate-a-process/38540fa8a050/index.html

  
**Step 1. Start**

Pick **Automate a process**, start **Blank** and **Continue to build**.

  
**Step 2. Wizard**

The **Wizard** lens has six sections. **Identity** names the flow. **Trigger** is the single entry point: manual, a schedule or a webhook. **Steps** holds the work in between; **Add a step** offers a Tool, Knowledge, a Skill, a Loop or Code. **Add branch** routes on a **Condition expression**; **Add approval** pauses for a human, with the **Reviewers / channel** to notify. **Output** names a **Destination**; **Guardrails** applies the safety profile to every step.

  
**Step 3. Visual**

**Visual** is the same draft on the canvas: the palette groups **Flow**, **Models**, **Agents** and **Tools**, and **Fit** frames the flow. Select a node for **Config**, **Input · Output** and **Policy**; an LLM step has a model, a **System prompt** with upstream variables, optional **Skills** and a Response format.

  
**Step 4. Code**

**Code** is a live, read-only serialisation of the canvas, with **Copy** and **Download**. **Copilot** takes a description of the change and proposes a whole workflow with its diff; nothing changes until **Apply to canvas**, and **Undo** is one click away.

  
**Step 5. Test**

**Test** runs the draft in the sandbox; every step reports in the **Run trace**, including the approval, auto-continued in the sandbox.

## Four lenses on one draft

![The Automate a process builder in the Wizard lens for a draft named GL Reconciliation: the build header with Setup, Test and Deploy, the lenses Wizard, Visual, Code and Copilot and Publish; the Build the flow rail with Identity, Trigger, Steps, Branches & approvals, Output and Guardrails; the Identity form with the workflow name, its slug gl-reconciliation and a description; and the Workflow draft rail counting nodes, steps, branches and approvals.](https://docs.katonic.ai/img/agents/automate-a-process/workflow-wizard.png)
*A workflow can be built as a form. The Wizard lens walks through trigger, steps, branches and output; the Visual canvas edits the same flow, and you can switch lens at any time.*

The build header offers **Wizard**, **Visual**, **Code** and **Copilot**, all editing the same autosaved draft. The **Workflow draft** rail counts nodes, steps, branches and approvals, and **Studio suggests** tells you when the flow is runnable: it needs a trigger, at least one step and an output.

## The Wizard lens

- **Identity**: the **Workflow name**, its slug and a **Description** that show in the registry.
- **Trigger**: the flow's single entry point. A trigger is manual, a webhook with a **Path**, or a schedule with a five-field **Cron expression** in the workflow's timezone.
- **Steps**: the work between trigger and output.
- **Branches & approvals**: **Add branch** routes on a value with a **Condition expression** such as `$class.intent`; the true and false routes are wired on the canvas. **Add approval** pauses for a human, with a label and the **Reviewers / channel** to notify.
- **Output**: the terminal node, with a label and a **Destination** such as returning to the caller, posting to a channel or writing to a table.
- **Guardrails**: the safety profile applied across every step.

## The Visual canvas

![The Visual canvas: the node palette on the left grouped into Flow, Models, Agents and Tools, the canvas with Trigger, LLM and Output nodes connected in a row and the zoom controls, and the Agent settings inspector on the right with name, description, owner team, default model, tier, guardrail toggles and the Topology summary.](https://docs.katonic.ai/img/agents/automate-a-process/workflow-canvas.png)
*The Visual canvas shows the workflow as nodes and connections. Drag nodes from the palette, connect them, and select one to configure it in the inspector.*

The palette on the left groups nodes: **Flow** (Trigger, Branch, Loop, Approval, Output, and **Visual**, a chart, metric or table node marked coming soon), **Models** (LLM), **Agents** (hand a step to a specialist agent) and **Tools** (a tool call, cited knowledge retrieval, a skill, an HTTP request and a code step). A **Visual** node has no runtime behind it, so dragging one on blocks publishing until you take it off again, and its own panel says so. The palette's other tabs hold **Templates**, the flow's **Vars** and **Files**.

With nothing selected, the inspector shows the agent's **Settings**: name, description, owner team, the **Default model** (Auto lets the gateway resolve it from the tier, and each node can override it), the **Tier**, three guardrail switches (**Customer-facing**, **Cost ceiling**, **Human-in-the-loop**, which inserts an approval gate before any write tool) and a **Topology** summary with estimated latency and cost per run.

![The canvas fitted to the flow from Trigger through LLM to Output, with the LLM node selected and a small toolbar above it to duplicate or delete it; the inspector's Config tab, scrolled to show Subtitle, Model, System prompt with Browse Prompt Studio and Insert variable, Pass the previous step's output in, Skills with Insert, Temperature and Max output tokens.](https://docs.katonic.ai/img/agents/automate-a-process/workflow-node-inspector.png)
*Selecting a node opens its configuration. An LLM step takes a model, a prompt that can reference upstream variables, optional skills and sampling settings.*

Selecting a node opens its configuration in three tabs: **Config**, **Input · Output** and **Policy**. An **LLM** step takes a step name, a model, a **System prompt** that can reference upstream values (**Insert variable** lists them, such as the trigger's message) or a prompt from Prompt Studio, optional **Skills**, temperature, maximum output tokens, a **Response format** of text, JSON or stream, and an output script. **Insert** on a skill copies its instructions into the step's prompt at that moment; a step sends one prompt and cannot resolve a skill version at run time, so later edits to the skill do not change the step. **Duplicate**, **Disable** and **Remove** sit at the bottom.

An **Approval** step names who can approve (anyone, a team or one person), the channel to notify, the time allowed and what happens when it runs out. A Member sees the pause as a request in the Work Room's Automations.

## The Code lens

![The Code lens: a file tree with workflow.yaml, tools.json and deployment.yaml under Config, agent.py under SDK, requirements.txt and .env.example under Deps and README.md under Docs, the read-only workflow.yaml open in the editor with Copy and Download, and the Call this agent panel with Python, TypeScript, HTTP and CLI snippets.](https://docs.katonic.ai/img/agents/automate-a-process/workflow-code.png)
*The Code lens is a live, read-only serialisation of the canvas. Copy or download the files to read the workflow as configuration, or to take it into your own tooling.*

**Code** is a live, read-only serialisation of the canvas: the workflow definition, a tools file and a sample deployment file under **Config**, a Python entry point under **SDK**, dependency files and a README, each with **Copy** and **Download**. The **Call this agent** panel shows sample calls for the published agent in several languages; the API endpoint is the one the Deploy tab shows.

## Copilot

![The Copilot lens: the palette and canvas as in the Visual lens, with the Workflow Copilot panel on the right inviting you to describe what to build or change, an example prompt and Send.](https://docs.katonic.ai/img/agents/automate-a-process/workflow-copilot.png)
*Copilot proposes a whole workflow from a description. Review what it proposes before applying it to the canvas.*

**Copilot** takes a description of what to build or change and proposes a whole workflow. Review what it proposes before applying it to the canvas; nothing changes until you apply.

If Copilot's pinned model fails, Copilot retries once on the reasoning tier. If no model answers, the panel names the model and provider; try again in a few minutes, or ask an administrator to pick another under **Platform Settings** › **Copilot**. A failure on the platform's side, such as an unreachable AI Gateway, is not retried.

## Test, publish and run

**Test** runs the draft in the sandbox and shows each step's trace. **Deploy** and **Publish** work as for any agent; see [Test, publish and versions](/agents/test-publish-and-versions). A published workflow gets a trigger endpoint that starts a run when a message is posted to it. Its page in Studio carries the run surface: **Triggers** (run now, the schedule from the trigger node, or the webhook), the run history with step progress, runs that are **Awaiting approval**, and outputs saved to Artifacts. Members start and follow runs from the Work Room; see [Start an automation](/user-guide/work-room/start-an-automation).

## Limits and behaviour

- The Wizard lens edits the branch condition; the canvas owns the edge labels.
- Skills inserted into an LLM step are copies. To keep a skill live across versions, use a **Skill** node with a version policy of following minor versions, following the latest, or pinning one.
- A published workflow cannot take a delegated turn from a coordinator; run it directly.

## Related

- [Create an agent](/agents/create-an-agent)
- [Automations and approvals](/user-guide/work-room/automations-and-approvals)
- [Skills](/agents/skills)
- [Prompt Studio](/agents/prompt-studio)

Source: https://docs.katonic.ai/agents/automate-a-process
