The four heights
The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.
Improve — make it easier to accept
+Before I circulate this report to the stakeholders, make it easy to scan — put the headline result…
Improve — make it easier to accept
+Before I circulate this report to the stakeholders, make it easy to scan — put the headline result (percentage of sites exceeding limit) on the first page, make the method names clickable to their appendix entries, turn the long raw tables into a one-page summary with clear hyperlinks to full tables, and flag any anomalies Tom Nguyen should explain.
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 lab results for site 14 and one instrument shows a high outlier while the backup…
Decide — diagnose the stuck moment
+I combined datasets and found one site with conflicting readings.
I merged lab results for site 14 and one instrument shows a high outlier while the backup instrument shows normal readings; Tom Nguyen wants the public summary by Friday but I don’t know which to trust. Describe likely causes for the conflict, recommend the immediate check I should do before finalizing the report, and the short note to add under site 14 to transparently communicate the uncertainty.
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.