Creating automations for your app

Use automations when you want to take work off your plate, such as sending summary emails, generating reports, syncing or cleaning up data, or running recurring maintenance tasks. When building an app in Base44, automations help you run backend functions automatically, on a schedule, when data changes, or when a connected integration sends an event through a connector. You create and manage automations using the AI chat in your app’s dashboard.

---

​

How automations work

When you create an automation, you choose how it starts. It can run on a schedule you define, in response to a data event such as a record being created, updated, or deleted, when an app user starts a conversation with an in-app agent, or when a connected integration sends an event using a connector. Each automation runs a backend function in your app and records the run so you can see what happened. Every automation has logs so you can always see when it ran, whether it succeeded, and any errors that occurred. This keeps everything transparent and easy to debug.

---

​

Types of automations

There are 4 types of automations you can create. When describing what you want to the AI chat, it helps to know which type fits your use case.

​

Scheduled automations

Scheduled automations run at a time or interval you define. Use these for recurring tasks like daily digests, weekly reports, or regular maintenance jobs. Example prompts:

• Send me a daily summary of all new orders to my email every morning at 8:00.
• Archive trip records that have been completed for more than 30 days, every Sunday at midnight.

​

Data event automations

Data event automations run in response to changes in your app’s data, such as a record being created, updated, or deleted. Use these to react to activity in real time. Example prompts:

• Send a push notification whenever I add a new WishlistPlace and write any needed backend function for me.
• Send the admin an email whenever a new booking is created.

​

In-app agent automations

In-app agent automations run when an app user starts a new conversation with an in-app agent. Use these to stay on top of who is reaching out, for example to get notified when a customer starts a chat, automatically add them to your contacts, or send yourself a summary at the end of the day. Example prompts:

• Email me whenever someone starts a new conversation with my agent.
• Add the person to my Contacts list when they start a chat with my agent.

​

Connector automations

Connector automations run when a connected integration sends an event, such as a new email arriving in Gmail or a calendar event being updated in Google Calendar. Use these to keep your app in sync with external tools. Example prompts:

• When a new email arrives in Gmail with the subject "Book appointment", parse it and add a new booking to my app.
• When a Google Calendar event is cancelled, update the booking in my app and post a message in the #salon-general Slack channel.

---

​

Creating an automation

When you click New Automation, Base44 shows suggestions based on your app’s context. You can pick one of those or click Create from scratch to choose your automation type and describe what you want in the AI chat.

​

Using a suggestion

Each suggestion includes a short description of what it does. Clicking one sends a pre-filled prompt to the AI chat, where you can review and adjust it before the AI sets it up. To create an automation from a suggestion:

1. Click Dashboard in your app editor.
2. Click Automations.
3. Click New Automation.
4. Browse the suggestions under Suggested for you.
5. Click a suggestion to send it to the AI chat as a pre-filled prompt.
6. Review the prompt, make any changes, and send it.
7. The AI sets up the automation and adds it to your Automations list.

---

​

Creating from scratch

If none of the suggestions fit what you need, create your automation from scratch. You choose the trigger type first, then describe what you want in the AI chat. To create an automation from scratch:

1. Click Dashboard in your app editor.
2. Click Automations.
3. Click New Automation.
4. Click Create from scratch.
5. Select the trigger type: Scheduled, Data event, In-app agent, or Connector.
6. In the AI chat, describe the automation you want. For example: Set up recurring email reminders to my email name@email.com for my tasks on my to-do list every Sunday at 17:00.
7. The AI creates the automation and adds it to your Automations list.

---

​

Managing automations

After you start using automations, you can control when they run, change their settings, trigger them on demand, or clean up automations you no longer need. You can pause automations without deleting them, and you can duplicate an existing automation when you want a similar setup with small changes.

​

Turning an automation on or off

Pause an automation at any time if you want to stop it running, and turn it on again when you need it. To turn an automation on or off:

1. Click Dashboard in your app editor.
2. Click Automations.
3. Click the toggle on the left of the automation name to turn it on or off.

---

​

Editing an automation

Make changes to an automation at any time. The changes affect future runs only. To edit an automation:

1. Click Dashboard in your app editor.
2. Click Automations.
3. Click the More actions icon on the automation.
4. Click Edit automation.
5. Update the automation details.
6. Click Save.

---

​

Duplicating an automation

Create new automations by duplicating existing ones and editing the new automation. To duplicate an automation:

1. Click Dashboard in your app editor.
2. Click Automations.
3. Click the More actions icon on the automation.
4. Click Duplicate.
5. Update the new automation’s details if needed, and click Save.

---

​

Running an automation immediately

Run an automation right away when you want to trigger its backend function on demand. This helps you test changes, confirm that your configuration works, or handle something urgent between scheduled runs. To run an automation:

1. Click Dashboard in your app editor.
2. Click Automations.
3. Click the More actions icon on the automation.
4. Select Run now.

---

​

Archiving an automation

If you do not need an automation anymore, you can move it to Archive to keep your active list clean. To archive an automation:

1. Click Dashboard in your app editor.
2. Click Automations.
3. Find the relevant automation in the list.
4. Click the More actions icon on the automation.
5. Click Archive.

---

​

Monitoring runs and using logs

Every automation keeps its own log so you can see when it ran, how long it took, and whether it succeeded. When something goes wrong, logs help you understand what failed and where to look in your backend code, without guessing. To view logs for an automation:

1. Click Dashboard in your app editor.
2. Click Automations.
3. Click the automation you want to inspect.
4. Click the Logs tab.
5. Review the list of runs, including the timestamp, duration, and status of each run.

---

​

Automations and integration credits

Each automation run typically uses ~1 integration credit, plus additional credits for any built-in integrations called inside it. For example, an automation that calls invokeLLM and sends an email costs the automation run plus credits for each action it triggers. See the full credit breakdown. Automations that run frequently or chain several actions can drain your credit balance quickly. Here are some ways to keep usage under control:

• Add specific trigger conditions. Narrow the criteria that cause an automation to fire so it does not run unnecessarily.
• Consolidate redundant automations. If multiple automations perform overlapping tasks, combine them into fewer, smarter workflows.
• Resolve failing automations promptly. Automations that error can still consume credits on each retry. Check your logs regularly and fix or disable problem automations as soon as you spot them.
• Review the frequency of scheduled tasks. Consider whether recurring automations, such as daily reports or reminders, need to run as often as configured.
• Minimize invokeLLM calls. Each invokeLLM call inside an automation is a separate credit charge. Only call the LLM when the result cannot be pre-determined.
• Test in a controlled environment first. Run automations manually on a small dataset and check the execution logs to estimate the per-run credit cost before enabling them at scale.
• Use Discuss mode when designing automations. Discuss mode costs roughly 0.3 message credits and lets you plan automation logic before applying changes, reducing trial and error.

---

​

FAQs

Click a question below to learn more.