Write an instruction once, and Hamster runs it automatically whenever the right thing happens in your workspace.
Every product team has tasks that should happen every time — summarise a new brief for the team, flag when a plan changes scope, check a completed task against your coding standards. Without automation, these rely on someone remembering to do them. Routines take those recurring jobs off your plate.
A routine has two parts:
When a trigger fires, Hamster reads your instructions, gathers the relevant context from your workspace, and executes. The output appears in the run history, and any changes it makes — to briefs, tasks, or documents — show up in the normal activity feed.
Open Routines from your workspace sidebar, then select New Routine.
The routine editor has three tabs:
Instructions are plain-language prompts. The AI receives the full context of the triggering event — the brief content, the task details, the initiative it belongs to — so you can reference "this brief" or "the task that was just updated" directly.
A few patterns that work well:
When this brief is created, write a two-paragraph research summary based on
the description and add it to the brief as a context document.
When a task is marked complete, check that the task title and description
match the acceptance criteria in the parent brief. If they don't align,
post a note in the task thread with the specific discrepancy.
When this blueprint is updated, compare the new version against the previous
version and summarise what changed in three bullet points.
Instructions can be as long as you need. Routines support full markdown, so you can include examples, formatting rules, or multi-step logic in your instructions.
Before a routine goes live, use Test Run to verify your instructions produce the right output.
Test runs don't require triggers to be configured first. Select Test Run from the routine modal and Hamster will execute immediately, using a sample event payload. The result appears in the Runs tab so you can review the output and adjust your instructions until you're happy.
When you're ready to go live, add triggers from the Triggers tab. You can test again at any point — test runs are logged separately from production runs so you can tell them apart.
The test-run button is disabled while a run is pending, or during the 30-second cooldown after a run completes. If your instructions are empty, the button is also disabled — you'll see a tooltip explaining why.
Triggers are workspace lifecycle events. Select one or more from the Triggers tab. Routines can have multiple triggers — a single routine can respond to both brief.created and brief.status_changed, for example.
Available trigger groups:
| Group | Events |
|---|---|
| Brief | Created, updated, status changed, deleted, document added/removed, task added/removed, member added/removed, comment added |
| Initiative | Created, updated, status changed, deleted, brief added/removed, member added/removed, comment added |
| Blueprint | Created, updated, deleted, published, section added/removed |
| Task | Created, updated, status changed, assigned/unassigned, completed, deleted |
| Plan | Generated, updated |
Each trigger can be enabled or disabled individually from within the routine, without removing it. Toggle the switch next to a trigger to pause it without losing the configuration.
Every routine execution is logged. Open the Runs tab inside a routine to see its execution history, or go to Routines → All Runs to see every routine execution across your workspace in one feed.
The run feed updates in real time — new executions appear as they complete, without refreshing the page.
Each run shows:
Click any run to open the full thread view with the complete input and output.
Creating, editing, and running routines requires the Manage Routines permission. Members without this permission can view routines and their run history, but can't create or trigger them.
Routine configuration is account-level. Routines you create apply to your whole team account — they're not personal automations.