> ## Documentation Index
> Fetch the complete documentation index at: https://datagen.dev/llms.txt
> Use this file to discover all available pages before exploring further.
# Triggers and Automations
> Enable an agent, run it now, and trigger it on a schedule or from a webhook with automations
Once an agent is enabled, it can run without anyone pressing a button. People reach it through chat, channels and the Agent API; **automations** run it on a schedule or when another system calls a webhook.
| Trigger | How it starts a run | Set up in |
| - | - | - |
| **Chat** | A message in **Chat** | Nothing to set up |
| **Test run** | Runs your unpublished draft | Agent Builder |
| **Run now** | Fires a saved automation once, on demand | **Automations** tab |
| **Schedule** | Fires an automation once at a set time, or on repeat | **Automations** tab |
| **Webhook** | Fires an automation when another system POSTs to its URL | **Automations** tab |
| **Channels** | A Slack, Teams or Discord mention, an email, a Linear issue, a public chat link | [Channels](/agents/channels) |
| **Agent API** | Your code sends a message to the agent | [Agent API](/api-reference/agent-api/overview) |
***
## Enable or disable an agent
An agent runs only while it is **Enabled**. The status pill at the top of the agent page shows **Enabled** or **Disabled**; click it to switch.
* **Publishing** from the Agent Builder enables the agent.
* **Disabling** stops it everywhere: chat, API calls, public links, email, chat apps, rooms and automations. Building and **Test run** in the builder keep working. Turn it back on to resume.
Only the Admin and Builder roles can enable or disable an agent.
***
## Automations
An automation is a saved invocation of the agent: a prompt, the triggers that fire it, and where its results go. Every firing is a real run of the agent, and each run starts a new conversation.
### Create an automation
On the agent page, open **Automations** and click **New Automation**.
Give it a **Name** (for example "Morning digest") and describe the task under **What should it do?**, for example: "Summarize last week's new leads and flag anything unusual."
Under **Triggers**, click **Add trigger** and pick **Scheduled** or **Webhook**. Add as many schedules as you need, plus one webhook. With no triggers, the automation runs only when someone presses **Run now**.
Open **Advanced settings** to pick **Destinations**, and optionally the **Model**, **Run as** identity and **Max concurrent runs**. The editor summarizes the choice as **Results go to: ...**.
Click **Create**. A webhook URL appears once the automation is saved.
| Setting | What it does |
| - | - |
| **Destinations** | Where each run's result is posted: **Web chat** (a new private conversation in your Chat list, titled after the automation) and the Teams or Discord channels the agent's chat apps operate in. See [Channels](/agents/channels). |
| **Model** | Overrides the agent's default model for this automation. Blank uses the agent's default, then the system default. An API-call model or a model pinned by the harness still takes precedence. |
| **Run as** | The API key that authenticates the run's calls back into DataGen. The key's owner is the run's identity. **Use account default** picks your default key when the run is dispatched. |
| **Max concurrent runs** | How many runs of this automation can run at once. |
| **Automation active** | When off, none of its triggers fire, whatever their own state. |
### Run now
Every automation row on the **Automations** tab has a **Run now** button that fires it once immediately. Run now is available to the Operator, Builder and Admin roles.
***
## Schedules
A **Scheduled** trigger runs the automation at set times, in the **Time zone** you choose.
| Frequency | Runs |
| - | - |
| **Once** | A single run at the **Date and time** you pick |
| **Every hour** | At the minute you pick, every hour |
| **Every day** | At the time you pick |
| **Every weekday** | Monday to Friday at the time you pick |
| **Every week** | On the day and time you pick |
| **Custom (cron)** | Any cron expression |
Custom cron examples:
| Schedule | Cron expression |
| - | - |
| Every day at 9 AM | `0 9 * * *` |
| Every Monday at 2 PM | `0 14 * * 1` |
| Weekdays at 8 AM | `0 8 * * 1-5` |
| Every 6 hours | `0 */6 * * *` |
A paused schedule shows **This schedule is paused.** with a **Resume** button.
***
## Webhooks
A **Webhook** trigger gives the automation its own URL. Any system that can send an HTTP POST can run the agent: n8n, Make, Zapier, GitHub, meeting recorders, your own apps.
The URL has this shape, and the editor shows it with a **Copy URL** button under **How to call this Automation**:
```text theme={null}
https://api.datagen.dev/api/agents//automations//trigger
```
### Protect the webhook
Under **API key (Bearer token)**, click **Generate** to require callers to send `Authorization: Bearer `. The key is shown once; DataGen stores only a hash, so save it immediately. **Rotate** issues a new key and stops the old one at once. Without a key, anyone with the URL can fire the webhook.
**Max calls per hour** limits how often the webhook can fire.
### Use the payload in the prompt
The JSON body you POST is available to the prompt. Write `{{ payload.foo }}` in **What should it do?** to insert the request's `foo` field:
```text theme={null}
Enrich the company {{ payload.domain }} and post a summary.
```
### Call it and get the result
```bash theme={null}
curl -X POST 'https://api.datagen.dev/api/agents//automations//trigger' \
-H 'Authorization: Bearer ' \
-H 'Content-Type: application/json' \
-d '{"domain": "example.com"}'
```
The response is `202 Accepted` with `{ executionId, statusUrl }`. The run starts asynchronously.
```bash theme={null}
curl 'https://api.datagen.dev/api/agent/execution/'
```
Poll every 1-2 seconds until `status` is final. The agent's answer is in `result.content`:
```json theme={null}
{
"executionId": "...",
"status": "completed",
"result": { "content": "" },
"startedAt": "...",
"completedAt": "...",
"durationMs": 10180
}
```
Click **Test fire** in the editor to POST `{}` to the URL and confirm it is queued.
For a request-and-response conversation with an agent from your own code, use the [Agent API](/api-reference/agent-api/overview) instead of a webhook.
***
Some older automations use the one-shot repo run, which can commit and open pull requests (**PR mode**: **Create PR**, **Auto Merge** or **Skip**). The editor shows a notice on these with a **Switch to conversation** button. New automations always run as conversations.
1. Check that the agent is **Enabled**.
2. Check that **Automation active** is on and the schedule is not paused.
3. Check the **Time zone** on the trigger.
4. Look for the run in [Agent Logs](/agents/versions-and-logs), filtered by the **Scheduled (Cron)** trigger.
* **401**: the webhook has an API key. Send `Authorization: Bearer `, or **Rotate** to get a new key if you lost it.
* **404**: check the agent name and automation id in the URL, that **Automation active** is on, and that the automation has an active webhook trigger.
* **429**: the webhook hit **Max calls per hour**, or you have too many queued or running runs. Retry after the time in the response.
## Next
Reach the agent from Slack, Teams, Discord, email, web chat and public links
Roll back a version and inspect every run
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.