Support data collection and reporting

Support data collection and reporting — real work, not an imagined feature: named inside 5 evidenced career tasks. Below are four ready AI prompts for it, one per height of help: do it, make it easier to accept, decide when you are stuck, and change the pattern for good.

5career tasks name it
4prompt heights

The four heights

The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.

Execute — do the immediate task

+
I need a single workbook that my team can use to collect weekly lab measurements from five field…
I need a single workbook that my team can use to collect weekly lab measurements from five field sites and produce one clean report for Monday morning. Combine the raw sheets I get from Anna, Jamal, Priya, Marco and Li into a reporting tab that shows each site’s last seven days, flags missing readings, and calculates the site average and standard deviation. Send it to me for a quick completeness check before I export the PDF for management on Monday.

Improve — make it easier to accept

+
Before I hand this to the monitoring team, make the week’s trends obvious and reduce entry errors.…
Before I hand this to the monitoring team, make the week’s trends obvious and reduce entry errors. Put the site average and a red missing-data badge in the top-left of the report, show a sparkline for each site’s seven-day trend next to its name, lock the cells I don’t want changed, and add a simple validation rule for the measurement column that rejects values outside historical limits.

Decide — diagnose the stuck moment

+
I just merged Anna, Jamal, Priya, Marco and Li’s CSV exports for the week and Site D’s standard…

I merged five different weekly files and one site shows wildly high variance

I just merged Anna, Jamal, Priya, Marco and Li’s CSV exports for the week and Site D’s standard deviation is three times normal. I don’t know if that is a true spike, a unit conversion error from Marco, or duplicate timestamps from Jamal. I’m worried management will panic if I hand this up. What’s the fastest sequence of checks I should run to diagnose the cause and what’s the best way to present my provisional finding to the lab manager so we don’t overreact?

Become — change the pattern

+
Every Monday we lose three hours reconciling different CSV formats, time zones and column names…

We repeatedly spend hours cleaning received files before reporting

Every Monday we lose three hours reconciling different CSV formats, time zones and column names from the five sites. It eats our day and invites mistakes. Tell me one habit to stop and one repeatable file-check I should impose on the senders so we can cut that time in half and avoid last-minute fire drills.

Where the evidence lives

Who was seen doing this, and what people really ask.

Software tasks in the LLOS Work Atlas come from evidence, never a feature list: careers attested to do the work, real job descriptions, and the questions people actually ask (with their view counts). Facets — feature, workflow, troubleshoot, administer, deploy, scale — are open metadata: the work decides, not a taxonomy.
Copyright © LLOS.ai · 2026 — original pedagogy, voice, and design — all rights reserved.

The rest of the map

Same library, five ways in.