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 have a sheet of survey counts, ticket sales and regional population by county for cultural…
Execute — do the immediate task
+I have a sheet of survey counts, ticket sales and regional population by county for cultural events. Send the cleaned market-research workbook to Maria in programming and to Raj in strategy for review with a Friday deadline — but first check every county has a clear demand metric and that the pivot summary matches the raw counts.
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 to the programming team, make it easy to act on. Bring the demand-per-capita…
Improve — make it easier to accept
+Before I hand this to the programming team, make it easy to act on. Bring the demand-per-capita figure to the top, add a small table showing overnight growth in attendance versus baseline, and flag any county where sample size is under 50 or trend is flat for three quarters so a programmer won't overbook.
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 merged last quarter’s phone survey with the online signups and the county totals changed; Maria…
Decide — diagnose the stuck moment
+I merged two county datasets and totals shifted.
I merged last quarter’s phone survey with the online signups and the county totals changed; Maria will assume the pivot is wrong and programming will book venues based on the first sheet. I don’t know which source should take precedence or whether duplicated respondents caused the shift. What is the most likely cause and the safest next step to reconcile counts before I send it to Raj and Maria?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+Every quarter we lose hours reconciling county totals after bringing in a new survey or signup…
Become — change the pattern
+We repeatedly rework county-level demand after merges.
Every quarter we lose hours reconciling county totals after bringing in a new survey or signup export. It costs trust with programming and pushes venue decisions late. Where are we most likely leaking time and credibility in our workflow, and what single habit could I change to stop late reconciliations and make the top-line demand metric reliable?
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.