Schedules & automations

Start with a working task#

From Automations, choose New → Chat to open the sidebar agent and send a setup request. The agent explains the workflow, uses your workspace context, and asks what should happen and when. Agree on the task, source records, destination, and timezone before creating it.

Every Monday at 9 a.m. in my timezone, summarize overdue tasks by owner and send me a short update. Do not change task statuses.

You can also test the task in an ordinary conversation first. Check the saved schedule rather than assuming that “tomorrow morning” means the same time to everyone.

Schedules and event triggers#

Choose New → Manual to configure a schedule or an event. Schedules run at a configured time, interval, or recurring schedule. For On an event, choose the event source:

• App: select an installed Opser app and one of the events it exposes. No connected integration account is required. The agent receives the event details when it runs.
• Integration: select a connected account and a supported event from that service.

The app picker shows app icons. If no apps are available, it shows No apps installed; an app without exported events shows No events available. Available apps and events depend on the workspace and the selected agent's access. The agent can discover these same app events when you create an automation in chat.

Review ongoing work#

New automations created in the setup form or through the agent run automatically by default. Creating one pre-approves the actions described in its task, including sending emails and updating app data. There is no separate app-access checklist or per-action approval prompt during those runs. Be precise about the intended actions and recipients.

Automatic execution still requires valid app permissions, connected accounts, and available usage credits. It does not grant new access. Older automations retain the authorization they were created with and may need to be recreated to use automatic execution.

Check the first run in History, open its conversation, and inspect the result before relying on it. If required access is missing, fix that access rather than repeatedly retrying the task.

When weekly-review email delivery is enabled for your workspace, a successful default weekly-review run can also send a report to the personal agent’s owner. Delivery depends on the available evidence, email preferences, and frequency limits. A failed run does not send its report. Review the result in the conversation and manage optional emails in Settings → Notifications.

For a failed scheduled run, ask the agent to inspect its diagnostics without rerunning it. The agent can show recorded errors, attempts and tool operations that your current conversation is allowed to receive. An attempted action does not confirm a saved change; check the affected records before retrying. Recorded detail can be incomplete, especially for older runs or worker interruptions.

Pause, edit, or remove#

Use the automation controls to pause, change, or remove work you no longer need. You can also ask the agent in chat to adjust an existing automation: it updates the schedule, task, timezone, or event source in place, so the automation keeps its identity, conversation, and run history instead of being deleted and recreated. If the automation changed in the meantime or a run is in progress, the edit is rejected rather than applied blindly.

Each automation lists its trigger with a distinct icon and label, so schedules, app events, and integration events are easy to tell apart. Review existing automations before creating a replacement to avoid duplicate runs. If a run fails or a connection is interrupted, inspect its history and the affected records before retrying: an action may already have completed.