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 compiled the weekly market activity spreadsheet and annotated the topline trends. Send the slide…
Execute — do the immediate task
+I compiled the weekly market activity spreadsheet and annotated the topline trends. Send the slide of key indicators to Maya in research and then to Tom in strategy for review, in that order, with feedback requested by Monday. Before sending, ensure the price change calculations are correct, the date ranges align, and that any outliers are explained or called out.
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 share this market-trends file with research, make it easy for Maya to interpret — put the…
Improve — make it easier to accept
+Before I share this market-trends file with research, make it easy for Maya to interpret — put the three most important trend numbers at the top, make the timeframe for each chart explicit, and flag spikes or drops with a short possible cause. Also list any data-quality concerns that would make a reader hesitate to act on the numbers.
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
+While updating the market activity sheet I saw a sudden trading-volume spike on July 12 that looks…
Decide — diagnose the stuck moment
+A sudden spike in trading volume appears in the sheet and I can’t tell if it’s genuine or a data error.
While updating the market activity sheet I saw a sudden trading-volume spike on July 12 that looks anomalous. Maya in research needs to decide whether to treat it as a real signal and Tom in strategy may react. I’m worried it could be a feed error or a duplicated row, but I don’t have access to the raw vendor feed to confirm. What quick checks should I run in the spreadsheet to diagnose whether this is a real market move or a data artifact, and how should I summarize the uncertainty to Maya so she can decide on action?
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 week we encounter one or two suspicious outliers in the market sheet that demand…
Become — change the pattern
+Recurring ambiguous outliers in weekly market reports force ad hoc checks.
Every week we encounter one or two suspicious outliers in the market sheet that demand time-consuming manual verification and slow decision-making for Maya and Tom. Where are we most likely wasting time — in how we ingest feeds, the lack of a raw-data snapshot, or in ad hoc QC — and which single habit should we change so 80 percent of these outliers are resolved or explained before the report goes to research?
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.
Behavioral EconomistDevelopment EconomistDevelopment Policy SpecialistEconomic Research AnalystEconomistHealth Economistalso: Analyze market trendsalso: Analyze data to identify trendsalso: Monitor market and industry trends
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.