2. The Basics: Build It Yourself
About ten minutes. This time you pass data from one step into another. Use Slack to send the result to a real app, or follow the no-account path with AI Prompt.
- Use it to
- Seed a Webhook trigger with sample JSON and map its fields into a Slack message or AI Prompt Step in about 10 minutes
- Find it
- Automations → Create new → Workflow
- Cost
- Slack path: 1 Step credit per test run · AI Prompt path: 0 Step credits + Glow AI tokens
- Output
- A formatted Slack message in your test channel, or {{ 2.result }} in the AI Prompt Step's Executions tab
What you will learn
- Placing steps on the canvas and connecting them
- Connecting an app so an automation can act on your behalf, if you use Slack
- Mapping data from one step into another
Before you start, complete Your First Automation or have a Glow account and workspace ready, and check your Step credits and Glow AI tokens.
Draft is not a sandbox: Run sends real messages. Pin write Steps or use test destinations; see How testing works. Choose No connected account in Step 2 to generate text in Glow with AI Prompt, or choose Slack to send a message to a test channel.
Step 1: Add a trigger
Start a fresh automation for this: in the sidebar open Automations, then click Create new → Workflow (or Create automation on an empty workspace), as in Tutorial 1. Every automation starts with a trigger: the event that wakes it up.
Replace the trigger placeholder
On the empty canvas, click + Add Trigger on the left-hand placeholder. The dock’s catalogue opens.
Add a Webhook
Under Tools → Start, click Webhook. It takes the placeholder’s spot on the canvas. Enable Body only in the Step’s setup so the posted JSON object’s fields appear directly in its output. The default setting puts them under body.
Give it test data
Click the step and open the Test & Debug tab. Testing data shows a sample object as a small structured editor. Hover over its top line and click the pencil icon: the object turns into editable text. Replace it with this sample, which matches the Body only output:
{
"visitor_name": "Ada Lovelace",
"message": "I would like a demo!"
}Press Cmd+Enter (Ctrl+Enter on Windows) to apply. The editor folds back into the structured view with your two fields.
Run it
Click Run step, then open the Executions tab. You will see the two fields you just entered, ready to map into the next Step. This replays your saved output; it does not verify a real webhook delivery or reshape the sample based on Body only.
A trigger with no data is hard to build against. You would be mapping fields you cannot see. Giving it test data first is the normal way to work, not a shortcut for tutorials.
Step 2: Add an action
A trigger on its own does nothing. Choose the path that fits what you can connect.
Slack
Add a Slack step
Open Apps in the dock at the bottom, search for Slack, and pick Post Message (or Send Message). It lands on the canvas; place it to the right of your Webhook.
Connect the steps
Drag from the dot on the right edge of the Webhook step to the dot on the left edge of the Slack step. That line is the execution order: Webhook first, Slack second.
Connect your account
Click the Slack Step and select or connect your Slack account in the Connection field (follow Connecting an App to authorize it), then pick your test channel from the Channel dropdown.
Step 3: Map the data
This is the part worth slowing down for. You will make the action use what arrived at the trigger rather than fixed text.
Click the data icon beside the field you are editing to open the Workflow data panel, then pick visitor_name under the Webhook step. Use the actual number shown on your Webhook Step if it is not 1, and continue with the path you chose in Step 2.
Slack
In the Slack step, put this in the Message field:
New inbound request from {{ 1.visitor_name }}:
{{ 1.message }}Why a number and not a name? Step references use the Step number, not its
display name. Renaming Step 1 does not change which Step {{ 1.message }}
refers to. Full syntax in Variable Reference Syntax.
Step 4: Run it and check the result
Check that the automation is still in Draft, then click Run in the dock. Glow executes both Steps using the test data from Step 1. On the Slack path, this sends a real message.
- Slack path: confirm your test channel received a message containing
Ada LovelaceandI would like a demo!. - AI Prompt path: open the AI Prompt Step, select Executions, and read the latest run’s
result. Expand the row if needed. Check that the greeting addresses Ada Lovelace and responds to the demo request.
That completes the tutorial. Leave the automation in Draft. If the expected result is missing, inspect the run’s error and follow Testing & Debugging. Check Slack before repeating an uncertain send.
Optional: accept live requests
Only enable automatic runs if you want to connect a real source to this Webhook. Complete the Before you turn it on checklist. For Slack, confirm the intended channel and message first.
Click the Draft status control and choose Live. Accepted requests to the Webhook’s URL can then start the automation automatically. Copy that URL from the trigger and send one controlled request. Confirm the same output checks from Step 4 before connecting ongoing traffic. See Webhook Triggers for setup and Operating Automations for checking automatic runs.
- Run
- Keep the automation in Draft and click Run in the dock using the saved Webhook testing data.
- You should see
- The Slack test channel receives the message with Ada Lovelace and I would like a demo!, or the AI Prompt Step's Executions tab shows a one-line greeting in result.
What’s Next?
You can now build an automation by hand and move data through it. Next is branching, which uses Slack and Google Sheets. If you want to keep learning without connecting accounts, read Mapping or Transforming Data and return to branching when those accounts are ready.