Calendar
Date-addressed scheduling — put work on a moment in time and let an agent do it when that moment arrives.
Routines answer the question "every how often?". The Calendar answers a different one: "at this moment." It is the only place in Command Center where work is addressed by a date and time rather than a cadence — and when that moment arrives, a Calendar entry does not run a script. It dispatches an agent.
That distinction is the whole point of the view. "Draft the quarterly summary every Monday" is a routine. "Work the migration mission on Thursday at 14:00, while I am out" is a Calendar entry.
You find it in the sidebar under Mission Control, between Missions Board and Email.
The layout
- The week grid is the main surface: day columns against a vertical hour axis, with entries drawn at their instant. Wider scales are available for looking further out.
- The header carries the two ways in — Sketches and New entry — plus the scale control and a health indicator that appears only when something needs attention.
- The composer rail opens on the right with two tabs, Entry and Sketch. It is both the creation surface and the edit surface; there is no separate modal.
- The occurrence drawer opens when you click a scheduled firing, and shows its status, its run history, and a link to the report the run produced.
Marking time is always live. On empty grid, one pointer gesture gives two outcomes by distance: press and release creates an entry at that time; press and drag marks an area. Hold Ctrl (⌘ on a Mac) while dragging to add a second area rather than replace the first. Re-marking while a form is open re-times it without discarding what you have typed.
The six kinds of entry
| Kind | What fires | Runs as |
|---|---|---|
| Agent task | A one-off job you describe in prose | An agent |
| Mission work | An action against a mission — work on it, activate it, or dispatch its fleet | An agent, in a workspace |
| Routine run | An existing routine, at a specific moment | The routine itself |
| Reminder | A notification for you | Nothing — it tells you |
| Scheduled email | A message you composed earlier, sent later | The mail engine |
| Note | An annotation on the calendar | Nothing at all |
The first two dispatch an agent; the middle two are mechanical; a note never executes. Every entry can be armed, paused, or archived, and every entry records who created it — you or an agent.
How an agent-dispatched entry runs
Two execution modes, chosen per entry:
Headless — the agent runs in the background through the same runner that executes routines. Nothing opens; the work happens and a report lands on disk. This is the right mode for work that needs no watching.
Workspace — the entry opens a grounded terminal workspace named after it, with one pane running a full agent session. You can watch it, read it, and intervene. Because the workspace is a surface of the app, this mode needs Command Center to be open when the entry fires; if the app is closed, the firing is recorded as missed rather than hanging silently.
Either way the entry is handed a brief — a generated file that states the job, names the strategic files to read by path, resolves any attached mission, and reserves the path the run must write its report to. You can read that brief before ever arming the entry: Preview brief in the entry dialog renders exactly what the run would receive, into a scratch location that cannot collide with a real dispatch.
A workspace run is considered finished when its report file appears, with a six-hour ceiling. A run that does the work but writes no report is recorded as a timeout — the report is the completion signal, not a side effect.
Autonomy — a ladder of reach
Every agent-dispatched entry carries an autonomy level, and the level is a statement about what the agent may do, not about how carefully it works:
| Level | The agent may |
|---|---|
| Report only | Read, investigate, and write its report. Nothing else changes. |
| Build | Also create and edit files in your workspace. |
| Full | Also act outward — send, publish, push. |
A mode has to be able to do the thing it is named for: an entry set to full whose job is "send the summary" is asking for the summary to be sent. What that reach costs is account — a run at full states in its report exactly what went out. Reversibility still binds at every level: no deleting without a backup, no overwriting someone else's work.
Set the level to the smallest one that can actually complete the job.
Sketches — describe the week, let an agent schedule it
Sometimes you know the shape of a week before you know its entries. A sketch is freeform intent written over one or more marked areas of the grid: "two deep-work blocks for the migration, and a review pass on Friday afternoon."
A sketch is inert by construction. It lives in its own store, and the clock never reads it — whatever it contains, it cannot fire. It becomes real only when you dispatch it, and then in one of two ways:
- Propose — the agent writes what it would create, and creates nothing.
- Configure — the agent creates the entries.
A configure run receives your text verbatim, each area in both your local time and UTC, and what is already scheduled in and around those areas, so it does not double-book you. Everything it creates is stamped as coming from that sketch, which gives you a one-action Undo this configuration — and the undo covers everything actually stamped, not just what the agent said it made.
Saved sketches stay on the grid as dashed, titled blocks. Click one to work on it, the same as any other object.
When something is wrong
A health indicator appears in the header only when there is something to see, and distinguishes four states:
- Failed — the run started and did not succeed.
- Missed — the moment passed with nothing able to run it (the usual cause is a workspace entry firing while the app was closed).
- Overdue — past its instant and still waiting on capacity.
- Misconfigured — armed but unable to ever succeed, such as mission work with no mission attached. This is the one worth acting on early: it is caught before the entry fails unattended.
Occurrences move through a visible lifecycle — scheduled, due, claimed, running, then one of succeeded, failed, timed out, missed, skipped or cancelled. You can re-run a firing that failed; the history appends rather than overwrites, so the earlier attempt stays readable.
The controls that govern it
Four independent switches, because authoring and firing are different questions:
- Calendar dispatch — the master switch for whether anything fires at all.
- Calendar control (Settings ▸ Agent control planes) — whether agents may author schedule. Turning it off refuses agent writes while agent reads keep answering, so an agent can still see what is scheduled and plan around it. It never gates you — your own edits are unaffected.
- Provenance — every entry records whether you or an agent created it.
- An audit log — every agent write to the schedule is recorded.
Two more knobs live in settings: how many scheduled runs may execute at once, and how far ahead the board is materialised.
This shape is deliberate. Oversight that works means being able to see, interrupt and disable — not a consent prompt per action, which trains reflexive approval and supervises nothing.
Where to go next
- Routines & automation — the cadence-addressed sibling, and how to choose between them
- Missions, operations & the fleet — what mission work entries act on
- Terminals — the workspace a workspace-mode entry opens
- calendar-mcp — the same surface for your own agents