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 to hand the latest habitat survey sheet to my supervisor and the regional planner for…
Execute — do the immediate task
+I need to hand the latest habitat survey sheet to my supervisor and the regional planner for sign-off by Thursday. Verify each transect row includes species counts, GPS coordinates, date and observer initials, and that the summary dashboard recalculates total effort before I send it.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Improve — make it easier to accept
+Before I issue this to the ecology team, make the monitoring sheet easier to act on: put recent…
Improve — make it easier to accept
+Before I issue this to the ecology team, make the monitoring sheet easier to act on: put recent declines and spikes on the summary row, make per-species trends findable, flag any transects missing coordinates or photos, and highlight which observations require an in-field follow-up within seven days.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Decide — diagnose the stuck moment
+The field crew uploaded yesterday’s transect counts and the dashboard shows a 30% higher total; the…
Decide — diagnose the stuck moment
+Field crew uploaded counts but totals don’t match the dashboard.
The field crew uploaded yesterday’s transect counts and the dashboard shows a 30% higher total; the team lead wants an explanation before tomorrow’s coordination call. I don’t know whether someone duplicated rows, a hidden formula is summing a helper column, or a wrong date range is included. What checks should I run in what order to quickly isolate the cause?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+We keep losing planner trust because the dashboard regularly shows different totals from the raw…
Become — change the pattern
+Repeated mismatches between raw field sheets and summary dashboard
We keep losing planner trust because the dashboard regularly shows different totals from the raw transect sheets. Over the last season the failures trace to duplicated imports, unchecked hidden columns, and inconsistent observer name entry. What habit change and one technical safeguard should I put in place so summaries match source data and we stop backtracking in meetings?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
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.