A trigger is work an agent does later, on its own: check CI half an hour after a push, summarize the open pull requests every morning, answer review comments when they land. Agents set triggers themselves when they have a reason to, so follow-through that used to depend on you remembering it just happens. You can also set one yourself from the Triggers page.
A daily trigger: when it fires next, every run so far, and the briefing each run starts from.
Turn it on
Open Agent features (under More in the sidebar), pick the computer your agents run on, and switch on Triggers under Tracking & automation. Runs happen on that computer, so it needs to be on and connected when a trigger fires.
Click How it works on the card for what it adds and a request to try.
Three kinds of trigger
Twelve hours of three triggers: one that fires once after a delay, one on a schedule, and one that fires on every review comment.
Once, later. "In 30 minutes", "tomorrow at 9". Good for following through on something just shipped.
On a schedule. "Every 4 hours", "every day". Good for standing duties: a digest, a sweep, a monitor.
On an event. A pull request opened, reviewed, approved, merged or failing its checks, a review comment, a push, an issue opened or assigned, and errors or failed jobs from your product's monitoring. Events need GitHub or Linear connected under Settings, Integrations.
Ask for it
"After you push, check CI in 30 minutes and fix anything red."
"Every morning at 9, summarize what merged yesterday and what's still open."
"When someone comments on this pull request, answer the comment and fix what it asks."
"Check back on the webhook retries backfill tomorrow and tell me if it finished."
"Pause the nightly sweep."
Agents set a trigger only when there is a concrete follow-up or an event worth reacting to.
Set one yourself
Click Triggers in the sidebar, under Automation, then New trigger.
Under Prompt, write what the agent should do. Title is optional.
Under When, pick now, in…, every… or on event, and fill in the time or the event.
Pick the Agent and, if you like, the Project folder it works in.
Tick read-only: report, don't change anything when the run should only look and tell you.
Click Set trigger. A review shows what will run, how often and what it may cost; confirm it there.
A new daily trigger: the prompt, every 1d, Claude, and read-only ticked.
The Triggers page
The page lists every trigger with its schedule, when it fires next and how its last run went. A strip across the top plots the last and next 24 hours of firings, and counts of recurring, one-time and failing triggers sit beside it; click one to filter. Search by title, prompt or last result, filter by recurring, one-time or event, and group by session or project.
Every trigger with its cadence, next firing and last result, under the 24-hour strip.
A trigger with a cheap way to tell nothing changed can skip a run. That shows as skipped in its history and costs nothing.
One trigger's page
Click a trigger to open it. Run now, Pause (or Resume), Cancel and Edit sit at the top. Below them: when it fires next, its cadence, how many runs so far, how the last one went, and where it runs. Run history lists each run; click one to open its conversation. Briefing is exactly what each run is told. Editing keeps the history, so you can still see what an older run was asked.
Anyone who can see the conversation that owns a trigger can see the trigger's page.
Where a run's result lands
A follow-up on a conversation's own work runs in that conversation: it arrives as the next turn, with the whole thread behind it, and the answer appears where the question was asked.
A standing duty runs in a fresh session each time, nested under the conversation that set it, so a daily job doesn't keep growing one thread. Each fresh run gets its briefing plus the previous run's summary. A clean run doesn't knock on your inbox; you read it under its trigger. You hear about it when a run fails, stops without reporting, or finishes with something you need to read or decide.
One run, opened from the run history. The bar at the top links back to the conversation that set it.
In the inbox and on your phone
The inbox has a Triggers line with how many are armed, when the next fires and anything that needs attention; open it for one row per trigger. A conversation tied to a trigger shows it in a bar at its top, with the time to the next firing.
The iPhone app has the same line in its inbox; long-press a row there to Run now, Pause or Resume it. The Tasks tab has a Triggers list too, each with when it runs next and how its last run went, where you can pause, open or cancel one. Runs that need you reach your phone like any other conversation that needs you.
The Triggers list on the phone, each with its cadence and next firing.
What it will and won't do
Triggers follow their conversation. Killing a conversation cancels its triggers; restoring it arms them again.
A usage limit pauses a run, it doesn't fail it. The run picks up where it stopped when the limit resets.
Read-only runs stay read-only. A trigger set to report only can look, but can't edit files or change anything.
Only the owner deletes. Teammates who can see a trigger can't remove it.
When something is off
What you notice
What to do
A trigger didn't fire on time
Check that the computer it runs on is awake and connected, then click Run now
An event trigger never fires
Connect GitHub or Linear under Settings, Integrations, and check the trigger names the right repository
A recurring trigger keeps showing skipped
Nothing changed since its last run, so it saved the run. Click Run now to force one
Runs are filling a conversation
Ask the agent to move the duty to a fresh session per run
For a fixed sequence of steps with approval gates, see Workflows. To run a whole plan across many agents, see Orchestration.