The team for this work
Which workers to hire, which Marketplace worker templates start them, and the order they need each other in.
✦ Guide · Intermediate
AI for engineering teams
Issue triage, sprint coordination, meeting actions and a Friday status as a team of flexible workers that reads your repository and your board, never the open web.
Start guideYOUR OUTCOME
You will run an engineering pod that labels every new issue, plans the sprint from the labelled list, turns stand-ups into owned actions and reports on Friday without inventing progress.
Triage reads the repo and the issue text, nothing from the web Plan from the labelled list, not the raw backlog A stale ticket is reported as stale, with its owner
4 min
Hire the first wave
Import, rename, and give a goal with the deliverable, the sources and the finish line.
The team and the second wave
Run the team in one room; hire the rest once the first deliverable exists.
The routine that keeps working
One recurring job on a schedule, then a status round and a grade.
What each lesson covers
The guide, lesson by lesson.
The team for this work
Which workers to hire, which Marketplace worker templates start them, and the order they need each other in.
Start from the work, not the tool: Issue triage, sprint coordination, meeting actions and a Friday status as a team of flexible workers that reads your repository and your board, never the open web. The team is Dev · Triage (Code review and issue triage), Cass · Sprint (Project coordinator), Notes · Actions (Meeting notes and actions), Friday · Status (Weekly status reporting). Each starts from a Marketplace template, imported as your own copy, renamed and re-goaled on the setup card; nothing personal and no creator credentials come with a template.
Practice. Open Marketplace, Worker templates, and read the Instructions and Integrations of each template on this list before you import anything. Note which sources each one will ask you for.
Marketplace → Worker templates → open Code review and issue triage. Read Instructions, then Integrations.
Hire the first wave
Import, rename, and give a goal with the deliverable, the sources and the finish line.
Import worker creates your copy as a flexible worker and opens the setup card. Rename it, replace the goal with yours, and choose When to work. Triage is the first hire because every plan and every report leans on issues that are already labelled, sized and de-duplicated.
Practice. Import Code review and issue triage, rename it Dev · Triage, and paste your goal on the setup card. Choose Now, once, and Continue. Check its first deliverable in Doc Manager before the next hire.
Name: Dev · Triage. Goal: Read the attached repository and the new issues in the attached export. For each issue attach an area, a severity, the file the stack trace points at, and any duplicate you find. Read only what I attached; if you cannot place an issue, say so rather than guess. When to work: Now, once.
The team and the second wave
Run the team in one room; hire the rest once the first deliverable exists.
Click New team, name it Engineering pod, add Dev · Triage, and post what the team is for. Then hire the second wave with goals that start by reading the first wave's document. @Name directs one member, @everyone the room, and Work in the member row opens what that member did in the team. The coordinator plans the sprint from the labelled list; the actions worker turns each stand-up into owned items with dates; the status worker reports only what the board shows.
Practice. Create Engineering pod, add each hire as it joins, and ask every member to post what it made and the one thing it would flag.
@everyone Welcome to the engineering pod. Dev's labelled issue list is in the workspace. Cass: plan a two-week sprint from it with owners and a capacity check. Notes: take today's stand-up transcript and post the actions with owners and dates. Friday: on Friday, report from the board only.
The routine that keeps working
One recurring job on a schedule, then a status round and a grade.
Issues arrive all day; a daily triage routine labels what came in overnight so the morning starts with a sorted list. Each run shows on its worker's Runs tab. Close each cycle with a status round, "@everyone one line each", and a grade against the acceptance checks each worker wrote first.
Practice. Add the time in When it runs, use Run now to get today's first report, then run one status round in Engineering pod.
When it runs → Add a time. Name: Daily issue triage. What should it do? Read the issues opened since the last run and attach an area, a severity, the file the stack trace points at, and any duplicate. Post the labelled list and mark anything you could not place. Repeats: Every day at 07:30.
Keep going
Make the learning stick
Start with one real piece of work.
Open Oppermind beside the lesson, apply each step, and leave with something you can use.