Cowork Tasks vs Routines
Tasks run now, Local Routines run on your machine, Cloud Routines run with the laptop closed. Where each one runs, what it can reach, and how to pick.
← Back to Reference HubBest for: One-off, interactive work that needs your local files, your open apps, and your judgment in the loop.
- Runs immediately in your open Cowork session
- Full local context: working folders, open-app awareness, Dispatch/computer use
- You stay in the loop — approve folder access, confirm risky actions
- Can be fired once on a delay (a one-off "in an hour" is still a Task, not a recurring routine)
- No persistence beyond the conversation — the work is the output, not a saved schedule
Limitations: A Task is gone once it runs — there's nothing to fire again tomorrow. If you find yourself re-typing the same prompt every morning, that's the signal to promote it into a Routine. Tasks also need you present (or at least the session open) to act on anything that requires confirmation.
Best for: Daily/weekly work that needs your local files or open apps and runs around hours when your laptop is on.
- Recurring — runs on a cron-style cadence or natural-language schedule
- Keeps local file access and open-app awareness, like a Task
- Created and managed with /schedule (list, edit, disable)
- Output lands back in a conversation — no separate inbox
- Missed runs queue and fire when you reopen Cowork
Limitations: Desktop-bound. If your laptop is closed at 6am, the 6am run does not happen on time — it fires when you reopen the app, which may be hours late. That's fine for a morning briefing you read at 8am; it's wrong for anything that must land on a strict clock or while you're away.
Best for: Must-run-on-time, off-hours, or always-on jobs that can get everything they need from connectors.
- Runs on Anthropic infrastructure — fires on time even with the laptop shut
- Best for strict schedules: pre-dawn briefings, hourly monitors, off-hours digests
- Connector-only data access — Gmail, Calendar, Drive, Slack, CRM, etc.
- No missed runs from a closed laptop — the cloud is always on
- Managed alongside Local Routines, but flagged as cloud-hosted
Limitations: No local file access and no screen awareness. If the job needs a file on your disk or an app you have open, a Cloud Routine can't see it. It also runs without you present, so its capability surface is exactly its connectors — scope those tightly (read-only where possible), because there's no one watching the run.
Best for: Promoting a Task you keep re-running into a managed, recurring routine.
- Trigger with /schedule or plain language ("every Monday at 9am, ...")
- Cron-style cadences or one-off fireAt times
- /schedule list shows everything you have running; update/delete to manage
- Choose local vs cloud where the cadence and capability needs make the choice clear
- Routines are revertible — disable without deleting the prompt
Limitations: Routines accrete. It's easy to schedule five things in a week and forget what's firing. Review /schedule list periodically and disable the ones you no longer read — an unread daily briefing is just noise that costs runs.
Best for: Knowing which routine type a job can even run on before you pick a cadence.
- Local-only signals: reads/writes a working folder, uses Dispatch, watches an open app
- Cloud-eligible signals: all inputs and outputs live behind connectors (MCP)
- Must-run-on-time + cloud-eligible → Cloud Routine
- Needs local context (any cadence) → Local Routine (or a Task if it's one-off)
- When in doubt, start local and promote to cloud once the job is connector-only
Limitations: Connectors carry the agent's authority and run unattended in a Cloud Routine — a misbehaving or compromised connector is a real risk vector with no human watching. Prefer read-only scopes for anything a Cloud Routine touches, and add write scopes only when you've watched the read flow work as a Task first.
A Cloud Routine runs without you watching — scope it like it
| Dimension | Cowork Tasks | Local Routines | Cloud Routines |
|---|---|---|---|
| Where it runs | Your open Cowork session | Your machine (desktop runtime) | Anthropic infrastructure |
| Recurring? | No — one-off (or a single delayed fire) | Yes | Yes |
| Runs with the laptop closed | No | No — queues until you reopen | Yes |
| Fires on a strict clock | Only while you're there | Best-effort — late if the lid was shut | Yes — on time, every time |
| Local file access | Yes | Yes | No |
| Open-app / screen awareness | Yes | Yes | No |
| Connector (MCP) access | Yes | Yes | Yes — its only data source |
| Human in the loop | Yes — you confirm risky actions | You see results next time you look | No one is watching the run |
| How you create it | Just prompt it | /schedule (default cadence) | /schedule, flagged cloud-hosted |
| Best for | Interactive, local, one-off work | Daily/weekly local work you read in working hours | Off-hours, must-run-on-time, connector-only jobs |
The two-question rule for picking the right one
Run any job through two questions, in order. (1) Does it recur? If no, it's a Cowork Task — do it now and stop. (2) Does it need anything on your machine — a local file, an open app, screen awareness? If yes, it must be a Local Routine. If no, ask the tie-breaker: must it run while you're away or on a strict clock? If yes, make it a Cloud Routine; if not, a Local Routine is the simpler default. The most common mistakes are scheduling an early-morning job as a Local Routine (it fires late, because the laptop was shut) and expecting a Cloud Routine to read a file on your disk (it can't — it only sees connectors).