Automate tasks with Botize

Triggers

The trigger is the event that starts the automation.

• 

  Get the next formula from Botize

  Go through each Botize formula one by one, extracting its content.

Actions

The action is what happens automatically, without you having to do anything else.

• 

  Run one of the user's Botize tasks (task-as-tool)

  Expose one of the account's Botize tasks as an agent tool: the agent launches it with input values and receives the task's final output when it ends — even if that takes hours (e.g. a human confirmation step). Bind with task_id FIXED (the task is pinned, never chosen by the model) and expose the task's declared input vars. The task must be ACTIVE and runs deterministically: whatever guarantees the user wired into it cannot be skipped by the agent.

• 

  Edit and save a Botize task

  Full-replace a task's definition with a modified microbot array (the SAME shape read_task returns under 'task'). Flow: read_task first, modify the array, then update_task with the FULL modified array. Validated against the real node; errors return as text to fix and retry. Preserves the task's active/paused state.

• 

  Read a Botize task's definition

  Return the full definition (trigger + steps + their parameters and {{vars}}) of one of the account's Botize tasks, so the agent can inspect it, explain it, or prepare an edit. Read-only. Pass the numeric task_id.

• 

  List the account's Botize tasks

  Return the account's Botize tasks as a list of {task_id, description, steps}, so the agent can show a menu or resolve which task the user means. Read-only, no parameters.

• 

  Inspect a task's recent runs (and why it failed)

  List a task's recent runs, with optional drill-down. Use the defaults first (level=summary) to scan cheaply; add status=error to go straight to the failures; and only then fetch one run's per-step detail with run_id + level=step (+ mb_id for a single step). An empty 'executions' list means no runs in the ~24h retention window, NOT that the task is healthy. To scan what SEVERAL runs received, use level=step with ONE field in include (e.g. include=input), max_field_len<=200 and limit<=25. 'outcome_counts' describes the whole window, and separates runs that completed from runs that stopped early without doing anything ('stopped_at' says where). In step payloads, 'data_omitted' marks data the server never stored; 'field_truncated' is just max_field_len and is harmless.

• 

  Activate a paused task

  Activate (start) a paused task so it attends its trigger/schedule again. Pass task_id.

• 

  Pause an active task

  Pause (stop) an active task so it stops attending its trigger/schedule until reactivated. Pass task_id.

• 

  Reschedule a task's next run

  Change the NEXT execution date/time of an ACTIVE scheduled task. Pass task_id and 'when' (absolute date-time or unix timestamp, at least 60s ahead). Only works on active interval tasks; a paused task returns an error.

• 

  Get related information

  Given a query, it provides related information such as video tutorials, automations, error solutions, and answers to inquiries.