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 field-observation log sent to the county conservation officer by Tuesday. Merge the…
Execute — do the immediate task
+I need the field-observation log sent to the county conservation officer by Tuesday. Merge the three CSVs from June fieldwork into one sheet, ensure each row has GPS coordinates, date, observer name (Sarah, Miguel, or Priya), and a photo link, then attach the file to an email for Sam in the county office. Before you send, verify there are no duplicate entries and that all dates are ISO format.
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 the field-observation spreadsheet to Sam in the county office, make it simple for him…
Improve — make it easier to accept
+Before I hand the field-observation spreadsheet to Sam in the county office, make it simple for him to find any habitat damage reports. Pull the damage rows to the top, show the nearest road and plot ID next to each GPS pair, make photo thumbnails easy to open, and flag observations older than 72 hours that might need follow-up. Highlight any missing observer notes that would make Sam hesitate to act.
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 two volunteers’ observation files and total counts for plot 12 disagree by 14%; the…
Decide — diagnose the stuck moment
+We uploaded two overlapping observation files and counts don't match
I merged two volunteers’ observation files and total counts for plot 12 disagree by 14%; the volunteers swear by their counts. The county contact, Sam, will be upset if we submit inconsistent data. I don't know whether this is a GPS offset, a transcription error, or different counting times. Given the raw sheets with timestamps and observer names, what is the most likely cause and what three quick checks will prove it one way or the other?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+Across every season we lose time cleaning volunteer spreadsheets: missing GPS, inconsistent date…
Become — change the pattern
+Field logs keep arriving with inconsistent formats and missing GPS
Across every season we lose time cleaning volunteer spreadsheets: missing GPS, inconsistent date formats, and photos not linked. This costs us credibility and forces manual fixes before submission. What three practical team habits or tools should we require so future field logs arrive uniform, verifiable, and ready to submit without a day of cleanup?
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.