Operations team runs daily data sync
An AI agent pulls reports, updates dashboards, and sends summaries every morning at 8am, without anyone pressing a button.
Set how often each employee checks its board and acts on its own, from every 5 minutes up to monthly, without you asking each time. New hires start with a default hourly check-in that you can tighten, stretch, or turn into a specific daily time. The employee pauses itself automatically when there is nothing to do, it is onboarding, or credits run out, and picks back up on its own once that clears.
Schedule any task and your employee executes it on autopilot. Set a daily research brief for 7 AM, a weekly analytics summary for Monday morning, and a monthly competitive report for the first of each month. Your employee runs each job on time, saves the output to its Drive, and notifies you when it is done. You wake up to finished work.
Each employee supports multiple independent schedules. Your marketing writer might have a daily social media content batch at 9 AM, a weekly blog draft on Tuesdays, and a bi-weekly newsletter draft on alternating Fridays. All three run independently. If one fails, the others continue. You see the status of every scheduled run in the activity feed.
Schedules are managed through chat. Say "run this research every Monday at 8 AM" and the employee creates the schedule. Say "cancel the weekly report" and it removes it. Say "change the daily brief to 6 AM" and it adjusts. No cron syntax, no scheduling UI. Just tell it what cadence you want.
Scheduled work has the same capabilities as interactive work: full tool access, memory, skills, and delegation. If a scheduled task requires reading from Google Sheets, sending an email through Gmail, and posting to Slack, it does all three. No capability restrictions just because you are not watching.
Scheduled work is called a routine. You can create one from chat, from the routines column on the task board, or straight from the calendar by clicking the slot you want it to run in. A routine carries a name, a cadence, and the work instructions the employee follows each cycle, and all three stay editable afterwards without rebuilding anything.
Cadence runs from a check every few minutes to once a day, with a custom interval for anything in between. A daily routine can be pinned to a specific time, so the Monday brief lands at seven in the morning rather than whenever the day happens to start. New hires begin with a gentle hourly check on their own board, which you can tighten, stretch, or replace entirely.
An employee with nothing to do does not run. If the board is empty, if the employee is still being onboarded, or if it is out of credits, the routine pauses itself and picks back up on its own once that clears, so an idle employee costs you nothing while it waits. Every run also records what woke it, so reading the timeline tells you at a glance which work came from a routine and which came from you.
Scheduled Execution lets your AI employees run recurring tasks without a human trigger. Set a daily briefing at 8am, a weekly competitor analysis every Monday, or a custom cron for end-of-month reporting. The agent wakes up, does the work, and saves the output to Drive, all without you opening a browser.
Each scheduled run has full tool access: web search, code execution, file management, connected apps. Your AI agent is not just firing a webhook. It is completing a real workflow, the same way it would if you assigned the task manually.
Most autonomous agents handle tasks you explicitly trigger. Scheduled Execution changes that. Define the task once, set the cadence, and your AI employee runs it reliably every cycle without reminders or follow-up.
Outputs land in the employee's Drive, so every scheduled run builds a history you can browse and reference. Week-over-week reports, daily digests, automated audits. The work accumulates. So does the value.
Sistava exposes daily, weekly, and fully custom cron syntax so operators can configure complex schedules without writing code. If your team already thinks in cron, it works exactly as expected. If not, the UI makes common patterns one click.
Scheduled tasks run in isolated agent contexts, so a long-running weekly job does not block your employee from handling real-time chat. Agentic AI working on your clock, not just on demand.
You set a schedule once and your AI employee runs the task at exactly the right time, every time, with full execution logs for every run.
Define a schedule using plain language or a cron expression: every weekday at 7 AM, every Monday at 9, the first of each month at 6 PM. Your AI agent treats scheduled tasks with the same rigor as tasks you delegate manually. It follows the same reasoning process, calls the same tools, and logs every step in the work journal.
Scheduled tasks can be as simple as a daily news summary or as complex as a weekly competitive analysis with web scraping, data aggregation, and a formatted report saved to Drive. The agent does not skip steps because it is running unattended. Every run produces a full execution trace so you can audit what it did and verify it completed correctly.
You are never left guessing whether a routine fired. Each cycle is checked before any work starts, so an employee with an empty board or a task that is waiting on you skips that cycle rather than spending a run on nothing, and the skip is recorded next to the runs that did happen. What did run lands in the work journal and the activity feed together with the reason it woke, so a month of routine output reads as one continuous record instead of a pile of disconnected jobs.
An AI agent pulls reports, updates dashboards, and sends summaries every morning at 8am, without anyone pressing a button.
The AI employee queues up social posts, newsletters, and blog updates on a fixed schedule, keeping the pipeline moving automatically.
An AI agent kicks off reconciliation, invoice checks, and report generation on the last business day of each month.
The AI employee processes ticket summaries and sends status updates overnight, so the team wakes up to a clean queue.
| Before | After |
|---|---|
| Someone has to manually trigger recurring tasks every day. | AI agents run on a fixed schedule, zero manual intervention. |
| Workflows slip when the responsible person is out. | Scheduled work runs regardless of who is in the office. |
| Cron jobs require engineering to set up and maintain. | Non-technical teams configure schedules directly in the platform. |
| Off-hours tasks pile up until someone logs in. | The AI employee works nights and weekends on schedule. |
Yes. Scheduled runs have full access to every tool the AI employee has been assigned, including web search, code execution, and connected apps like Gmail or Notion. There is no reduced capability for automated runs.
Output is automatically saved to the employee's Drive and logged in the Work Journal. You can browse results any time without waiting for the next run.
Both. Sistava supports preset options (daily, weekly, monthly) and full cron expression syntax for precise scheduling like every weekday at 7:45am or the first Monday of each month.
The failure is logged in the Work Journal with details on what went wrong. You can review the error, adjust the task, and re-trigger manually or wait for the next scheduled run.
Yes, you can configure any AI employee to run on a cron schedule, daily, or weekly cadence without manual triggers. Just define the task and the schedule, and the agent executes it automatically at the right time.
Cadence ranges from a check every few minutes to once a day, with a custom interval available for anything in between. A new hire starts on an hourly check that you can tighten or stretch at any time, and a daily routine can be pinned to a specific time of day.
Yes. Open the task and choose to make it recurring, and the routine opens with the title and work instructions already carried over. You pick the cadence, save, and the same piece of work now runs on its own every cycle instead of waiting for you to re-create it.
Every routine has its own on and off switch, so you can pause one without losing its work instructions and switch it back on later. Employees also pause themselves when there is nothing on the board worth acting on, and resume on their own the moment real work appears.
I set up a Monday morning market brief that runs at 7 AM. It pulls live data, writes the summary, and has it in my inbox before I open my laptop. Took five minutes to configure.
Set Your Employee's Working Hours is part of Where their work lives.
Your AI agents manage their own workspace. Scheduled tasks run daily, weekly, or on custom cron cadences. A built-in kanban board tracks what is in progress. Every document lands in a personal Drive. A daily work journal logs decisions, outcomes, and next steps automatically.