The team for this work
Which agents to hire, which Marketplace templates start them, and the order they need each other in.
✦ Guide · Intermediate
AI for data teams
Spreadsheet checks that tie every metric to its source rows, a Monday metrics report with the week-on-week change, pipeline failure triage and sourced research as a team of agents.
Start guideYOUR OUTCOME
You will run a data pod that refuses to report a metric whose formula chain does not tie, publishes Monday metrics with the change and the source, labels pipeline failures by failing step, and researches with citations.
A metric is reported only when its chain ties back to the source rows Monday numbers carry the week-on-week change and their source A pipeline failure is handed over as the log and the pipeline file
4 min
Hire the first wave
Import, rename, and give a goal with the deliverable, the sources and the finish line.
The group 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 agents to hire, which Marketplace templates start them, and the order they need each other in.
Start from the work, not the tool: Spreadsheet checks that tie every metric to its source rows, a Monday metrics report with the week-on-week change, pipeline failure triage and sourced research as a team of agents. The team is Sol · Checks (Spreadsheet review and reporting), Monday · Metrics (Weekly status reporting), Dev · Pipelines (Code review and issue triage), Ren · Research (Research assistant). 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, Agent 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 → Agent templates → open Spreadsheet review and reporting. Read Instructions, then Integrations.
Hire the first wave
Import, rename, and give a goal with the deliverable, the sources and the finish line.
Import agent creates your copy and opens the setup card. Rename it, replace the goal with yours, and choose When to work. The checks agent is the first hire because a metric nobody has tied back to its rows is a rumour with a chart.
Practice. Import Spreadsheet review and reporting, rename it Sol · Checks, 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: Sol · Checks. Goal: Review the attached metrics workbook. For every headline metric, trace its formula chain back to the source rows and report whether it ties; list every cell where a hard-coded number sits over a formula and every reference to a sheet that no longer exists. Do not change the workbook. When to work: Now, once.
The group and the second wave
Run the team in one room; hire the rest once the first deliverable exists.
Create group chat, name it Data pod, add Sol · Checks, 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, Work ↗ opens a member's own session. The metrics agent reports only metrics that passed the checks; pipeline failures are labelled from the log and the pipeline file; research carries citations.
Practice. Create Data 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 data pod. Sol's checks table is in the workspace. Metrics: report this week's headline numbers, only the ones Sol marked as tying, with the week-on-week change and the source cell. Dev: triage the attached failing job log against the attached pipeline file. Ren: research the benchmark question with sources.
The routine that keeps working
One recurring job on a schedule, then a status round and a grade.
The Monday report is the same job every week; a routine runs it before the team arrives. Every run is a session under Finished today. Close each cycle with a status round, "@everyone one line each", and a grade against the acceptance checks each agent wrote first.
Practice. Create the routine, use Run now to get today's first report, then run one status round in Data pod.
New routine. Name: Monday metrics. Instructions: Read the metrics workbook and the exports added since the last run. Report each headline metric with its week-on-week change and the source cell, and omit, by name, any metric whose formula chain does not tie. Frequency: Every week, Monday, 08:00.
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.