Assignments

An assignment is a job described once and run many times: a name, the instructions the agent follows each run, and the triggers that start it. Assignments belong to an agent and open from the Assignments card on the agent’s page.

Assignments are the step from delegation to routine. A conversation gets you one answer; an assignment gets you the same job done every Monday morning, or every time another system calls a webhook, without anyone remembering to ask. Each run is a session — the full record of what the agent did — so a recurring job builds its own audit trail as it goes. Most of the standing work in a workspace ends up here: the weekly report, the maintained tracker, the triage of whatever arrived overnight.

Creating an assignment

On the agent’s page, open the Assignments card and choose Add assignment. The assignment is created straight away and opens on its own page, where edits save as you make them. Name it in the title, then work through the tabs:

Instructions — the job prompt: what the agent should accomplish each run. The AI-assist button drafts instructions from a short description, using the agent’s personality as context. Be explicit about the deliverable; “produce a document with a summary table and week-over-week changes” beats “summarize the pipeline.”
Schedule — the triggers. Every assignment can run on demand, and can also run on a schedule or from a webhook. See Schedules, webhooks, and triggers.
Options — Budget & effort (a session budget, plus the model — Tactical, Strategic, or Operational — and the effort, Low through Max, each run uses), parameters the run receives, skills and integrations every run should use (by default the agent decides), and a suggested deadline in minutes.
History — every past run, its outcome, and a link to the session it produced.
Hooks — a read-only view of any follow-up actions defined for the assignment: what it may reach, what it validates, and what it does when a run completes.

If the agent needs accounts connected before it can run, the page says so above the tabs, with a button for each gap, and shows whether the work runs as you or on a company account. Press Run now in the header to start a run immediately.

A complete example

Here is the assignment the weekly report guide builds, written out tab by tab.

Name — Weekly Pipeline Report.

Instructions —

Every Monday, pull the open opportunities from the CRM. Produce a document with a summary table of pipeline by stage, the top five at-risk deals with a one-line reason each, and week-over-week changes in total value. Call out any deal that changed stage since last week. Keep the whole thing to one page — it gets read on phones before the Monday standup.

Schedule — Weekly, Mondays 6:00 AM, America/New_York.

Options — the CRM integration is listed under integrations every run should use, so no run skips it; no parameters, no deadline, and Budget & effort stays on its defaults for a routine job like this.

Press Run now and watch the first session. If the report isn’t right, refine the instructions and run again; the schedule takes over once you’re happy with the output.

From conversation to assignment

If you find yourself asking an agent for the same thing repeatedly, turn the conversation into an assignment: Save as Assignment on a session drafts one from the full back-and-forth — name and instructions distilled from what the agent actually did — and Edit & Save turns the draft into a real assignment for you to review and schedule. This is often the easiest way to write good instructions: a real conversation shakes out the ambiguities before anything lands on a schedule.

Finding assignments

The agent’s Assignments card shows how many it has and when the next one runs. Open it for the active ones, soonest next run first, with a link to any it has completed. The Assignments tab beside Agents lists the standing work of every agent in the workspace, filterable by agent and by status (active, paused, or completed) and sortable by next run, last run, or name. Each run appears in the agent’s sessions and on the assignment’s History tab, so what ran last Monday, and how it differed from the Monday before, is always one click away.

Every agent also reviews its own week once a week. That reflection is the platform’s, not one of your assignments, so it stays out of these lists and its sessions stay out of the sidebar; read it, and choose when it runs, on the agent’s Reflections tab.

Assignments can also surface where the team tracks its work: a board can adopt an existing assignment as a task, and from then on the board manages its schedule and instructions. Its page says so and links to the task, and it completes when that task reaches Done.

Pausing

Each assignment has a switch in its header that pauses its automated triggers, and the agent’s Assignments card opens onto a master Automated runs switch that quiets everything at once. Run now keeps working either way — pausing stops the automation, not the job. Reach for the per-assignment switch while you rework one job’s instructions; reach for the master switch when the whole agent should go quiet, over a holiday week or while you reorganize its workload. Turning the master switch back on returns each assignment to its own paused or running state.

Deleting an assignment removes its configuration for good; past runs and the sessions they produced are kept.

When something goes wrong

A run that hits a blocker — expired credentials, missing data, an ambiguous instruction — escalates to your Inbox with a priority rather than failing silently. Fix the blocker, reply, or rerun. The practical consequence is that you don’t need to check whether the Monday report ran: if it did, the deliverable is there, and if it couldn’t, the Inbox says so and tells you why.

Patterns that work

Standing report — a weekly or monthly schedule with a document deliverable: pipeline, support volume, campaign performance. The weekly report guide is the worked version.
Maintained surface — the job is to keep a data table current rather than to produce a fresh artifact each run; see the agent-maintained table guide.
Event-driven work — a webhook trigger, so a run starts when a ticket, form submission, or deploy happens in another system; see triggers.
On-demand playbook — no standing trigger at all: a codified job you start with Run now whenever the situation calls for it.