A new teammate,nothing forgotten.
Tell the lead agent who joins and when. It writes the checklist, puts the work on a board, and you give each task an owner — a helper drafts the access requests, the lead plans the first week, and the welcome message waits until the accounts exist. Every morning its daily prompt reads the checklist and, with your OK, reminds whoever is holding a step up in the team chat.
Day one: checklist and requests. Next morning: a nudge, two answers, the blocked task goes out. Allow the nudge when asked.
The lead builds a checklist and a board; a helper drafts access requests; next morning the daily prompt nudges the owners and the blocked welcome goes out.
One checklist
A to-do card both of you edit: the lead ticks steps as answers come in, you can click any step yourself.
Tasks with owners
Each task on the board is assigned to one agent; auto-dispatch sends it only to that agent.
Blocked until ready
The welcome message depends on the access task and goes out by itself the moment that task is done.
Nudges, not nagging
The morning prompt reminds only the owners of waiting steps, in one message, after you allow it.
From “she starts Monday” to a ready first day
Two agents, a checklist, a board and the team chat.
More in Workflows
Other live scenarios from the same shelf — and a few close relatives.
Weekly report, assembled by a team
WorkflowsA lead agent sends two helpers for sales and support numbers, merges them, and posts to the team after your OK.
AgentBrowserNoteTelegramDocument intake with a second opinion
WorkflowsScans go on a Reference card, one agent extracts the fields, a second model checks them, and files move after your OK.
AgentTask boardReferenceBudgetWorkflows
Beyond codeDaily prompts, web watches and Telegram messages that set agents to work.
AgentBrowserTerminalNoteTo-do listTelegramStandupEnd-of-day wrap-up
On a scheduleAt 18:30: board and git read, a stray branch pushed, tomorrow’s list written.
AgentNoteTo-do listTask boardStandup
Give every new hire a first day that works
The agents track it; people do only their part.
macOS and Linux are coming later.
The first-run wizard installs an agent CLI, Git and the dictation model for you — or skips each step.