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 the weekly KPIs for the executive meeting. Build the report and charts, then email the PDF…
Execute — do the immediate task
+I need the weekly KPIs for the executive meeting. Build the report and charts, then email the PDF to Priya, the branch manager, and Sam, the planning director, with a note that the visuals are for the 10 a.m. review on Thursday; confirm the underlying data covers Monday through Sunday and that the trend chart uses consistent scales.
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 hand this dashboard to Sam and Priya, make the visuals faster to scan: surface the three…
Improve — make it easier to accept
+Before I hand this dashboard to Sam and Priya, make the visuals faster to scan: surface the three headline metrics at the top, convert the stacked bar into a small-multiples view so each region stands alone, annotate any week with a variance over ten percent, and move the data table to the end so reviewers can validate numbers if they want.
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
+I updated the KPI dashboard and the trend line for conversions has a sharp spike in week 14. Priya…
Decide — diagnose the stuck moment
+The trend chart spikes on week 14 and no one knows why.
I updated the KPI dashboard and the trend line for conversions has a sharp spike in week 14. Priya will ask about it in the Thursday review and I need an answer. I don’t know if this is a data load error, a real campaign effect, or a filter mismatch. What are the quickest diagnostic steps to prove whether week 14 is valid and what to prepare to explain it to Priya?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+Over six months we keep reformatting dashboards for the execs but they only focus on two numbers…
Become — change the pattern
+We waste hours polishing charts the execs ignore.
Over six months we keep reformatting dashboards for the execs but they only focus on two numbers and ignore the rest; prep time is draining planning. What change in how we build and circulate weekly visual reports would save five hours a week and actually get the branch manager to engage with the right metrics?
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.
Algorithm EngineerDatabase AnalystEducation Policy AnalystOptimization EngineerSports StatisticianStatisticianalso: Produce reportsalso: Write statistical reports
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.