Set up prompts that run on their own

Scheduled tasks let Babbily run a saved prompt on its own and leave the answer in a new chat. They suit recurring briefings, inbox or calendar summaries, weekly reviews and topic monitoring. They’re available on paid plans, and each run uses the API usage budget of the workspace where the task is saved.

Create a task

1. Choose a workspace. Switch to Personal or the team workspace where the task should run. Tasks don’t move between workspaces.

2. Open Scheduled. Choose Scheduled in the sidebar, then New task, or start from a template.

3. Write the prompt. Give the task a clear name and include everything Babbily should know, since nobody will be there to answer a follow-up question.

4. Choose the model and frequency. Pick a supported model, schedule, time and time zone.

5. Choose Plugin access. Select the connected Plugins the task may read from, then save when the summary matches what you expect.

A workspace can hold up to 10 personal Scheduled tasks or 25 team Scheduled tasks.

Pick a schedule

• Manual runs only when you choose Run now.

• Hourly runs every hour at :00, :15, :30 or :45.

• Daily runs every day at the selected local time.

• Weekdays runs Monday through Friday at the selected local time.

• Weekly runs on the selected weekday and local time.

• Monthly runs on the selected day and local time. Shorter months use their last day.

Babbily stores each task’s time zone, shows the next run in that zone and handles daylight-saving changes from the local schedule you chose.

Run, pause and review

Run now starts an extra run without waiting for the next scheduled time, and Babbily won’t start a second run of the same task while one is already active. Use the task switch to pause or resume future runs.

Expand Recent runs to see queued, running, completed, skipped, failed or canceled runs, and to open the chat a completed run created. Those chats don’t appear in the normal Library or recent-chat list, so open them from the task. Deleting a task removes its run history from Scheduled, so save anything you need first.

Scheduled tasks always run on a named model, and Auto isn’t available for them. If a task’s model is retired, Babbily runs it on an available replacement and labels the run. Edit the task to choose a model yourself, because a replacement can use more of your budget than the original.

Use Plugins safely

Scheduled runs are unattended. A selected Plugin can read authorized context, but it can’t perform a write action that would normally pause for your approval. Scheduled tasks also can’t run Deep Research, artifact actions or past-chat lookup, so put the context the task needs into its saved prompt.

If a task needs to send a message, update a record or change a document, use an attended chat instead. A prompt can still be saved when no suitable Plugin is selected, so read any capability warning before saving, especially for calendar, email or workspace requests.

Tasks in a team workspace

Accepted team members can view, edit, run, pause and delete tasks in their team workspace. Editing a task changes its Runs as identity to the editor, so future runs use that member’s connected Plugins. Everyone in the team can read a run’s result, but only the member shown in Runs as can continue that chat. If the team plan becomes inactive, members can still pause or delete tasks, but new runs wait until plan access is restored.

When a run is skipped or fails

Every run checks the workspace plan and API usage budget before it starts. A run can be skipped or fail when:

• The paid plan is no longer active or can’t be verified.

• The workspace API usage budget is used up.

• The selected Plugin needs reconnecting or reselecting.

• The task is already running.

• The selected model is unavailable and no replacement can be used.

Open Recent runs for the result and try the suggested action before running the task again.

Read the full docs ↗