Skip to content

2.9. Automations

The Automations page (sidebar > Automations) runs inference tasks on a schedule, with no one at the keyboard: a daily summary of a folder of documents, an hourly status check against a URL, a weekly report draft. Each automation pairs a model (and optionally an agent) with a prompt template, an input source, and an output action.

The page has three tabs: Automations (the list), Execution History, and Container Tasks. Container Tasks shows scheduled jobs that run inside containers; see Container Task Scheduling.

Creating an Automation

Click New Automation and fill in the form:

  1. Basic Info: A name (e.g., "Daily summary", "Hourly check").
  2. Schedule: Pick a frequency preset (every 15 or 30 minutes, hourly, daily, weekly) or write a cron expression directly; the expression is validated as you type. The timezone uses IANA names (e.g., Asia/Seoul, America/New_York).
  3. Model & Agent: Choose the model that runs the task. The Agent field defaults to None (direct inference), which sends the prompt straight to the model; selecting an agent profile runs the task through that agent instead. Three toggles control the model lifecycle:
    • Auto-load model before execution: load the model if it is not already in memory.
    • Unload model after execution: free the memory once the run finishes.
    • Catch up missed executions on startup: if the app was closed at the scheduled time, run once at the next launch.
  4. Tools: Select which tools the model may call during the scheduled run. With no tools selected, tool calling is disabled for the run.

  5. Input Source: Optional external data injected into the prompt as {{input}}:

    • None: no external input.
    • File: the content of a file path.
    • Directory (glob): files matching a glob pattern (e.g., /data/docs/*.txt).
    • URL (HTTP GET): the response body of a URL.
    • Shell Command: the output of a command.

    Shell commands

    Shell commands run with the app's permissions. Only use commands you trust.

  6. Prompt: An optional system prompt plus the prompt template sent to the model.

  7. Output Action: What happens to the result:
    • Store in history only: visible in Execution History.
    • Save to file: written into a directory you choose.
    • Desktop notification: shown as an OS notification (the form requests notification permission if not yet granted).
    • Webhook (HTTP POST): posted to a URL.
  8. Parameters: Generation settings for the run, including temperature (0 to 2) and max tokens.

Template Variables

The prompt template (and system prompt) can include variables that are resolved at run time:

Variable Resolves to
{{input}} Data from the input source
{{date}} Current date (YYYY-MM-DD)
{{time}} Current time (HH:MM:SS)
{{datetime}} Full ISO 8601 timestamp
{{prev_result}} Result of the previous execution
{{file:/path/to/file}} Inline file content (up to 100 KB)
{{env:VAR_NAME}} Environment variable value (known sensitive variable names are blocked)

Managing Automations

Each automation card shows the model, the schedule in plain words (e.g., "Daily at 09:00"), the last run result, and the next run time. From the card you can:

  • Toggle between Active and Paused without deleting the automation.
  • Run Now to trigger an immediate execution outside the schedule.
  • Edit the configuration.
  • Delete the automation. This also removes its execution history; a confirmation dialog asks before proceeding.

Desktop notifications announce when a run starts, completes (with its duration), or fails.

Execution History

The Execution History tab lists every run with its automation name, status, start time, duration, and result. Filter by automation, status, or date range, and open a run to inspect its full result or error.