The four heights
The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.
Execute — do the immediate task
+Finalize the pollutant source investigation spreadsheet for the creek sampling: enter lab results…
Execute — do the immediate task
+Finalize the pollutant source investigation spreadsheet for the creek sampling: enter lab results for sites C1 through C8, calculate exceedances against the regulatory thresholds, assign a likely source ranking for each site, and send the file to Priya in environmental compliance with a one-day advisory note on sites exceeding thresholds.
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 forward the investigation to compliance, make the findings easy to act on: put exceedance…
Improve — make it easier to accept
+Before I forward the investigation to compliance, make the findings easy to act on: put exceedance counts and the top three contaminants at the top, make thresholds and units obvious next to each result, flag any inconsistent sampling dates or missing chain-of-custody entries, and call out sites where multiple contaminants indicate the same upstream source so Priya can prioritise field follow-up.
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
+Site C5 returned high nitrate and copper simultaneously, which is unusual. I’m worried this…
Decide — diagnose the stuck moment
+One site shows spiked levels of both nitrate and copper in the latest run.
Site C5 returned high nitrate and copper simultaneously, which is unusual. I’m worried this indicates a mixed source like agricultural runoff plus illegal disposal, but I don’t know if the lab mixed samples or if the field notes missed a spill. I can’t tell whether to treat it as lab error or a real mixed-source event. What’s the most likely diagnosis and the immediate steps to confirm it before recommending a response 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
+We keep wasting days chasing lab results because field teams omit sample times, sampler initials,…
Become — change the pattern
+Too many follow-ups because samples lack consistent metadata from field teams.
We keep wasting days chasing lab results because field teams omit sample times, sampler initials, or site photos; over the past year that added a week to investigations. What one change to the sample intake procedure and one habit for field teams should I implement so future lab results are actionable on arrival and reduce back-and-forth with compliance?
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.