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 to confirm attendance and satisfaction trends for last week's gallery opening. Send the…
Execute — do the immediate task
+I need to confirm attendance and satisfaction trends for last week's gallery opening. Send the attendee list, survey totals, and the two-page summary of follow-up actions to Emma, the Artist Liaison, and Sam, the Conference Manager, for their sign-off by Friday. Check that survey response rates and open comments are visible and that all artist names match the roster before sending.
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 satisfaction report with the curators, make the key signals obvious: show…
Improve — make it easier to accept
+Before I share this satisfaction report with the curators, make the key signals obvious: show average satisfaction at the top, highlight any sessions under 3.5, pull the three most-cited complaints into a single paragraph, and flag any artists whose attendees reported below-average experience. Make the findings scannable for Emma to approve quickly.
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
+At last night's reception average satisfaction fell from 4.5 to 3.2 for the 7–9pm slot. Emma and I…
Decide — diagnose the stuck moment
+Survey shows a sudden drop in satisfaction for one evening
At last night's reception average satisfaction fell from 4.5 to 3.2 for the 7–9pm slot. Emma and I are split on whether it's a one-off or a systemic problem. I don't have reliable timestamps for each comment, and I can't tell if a single artist's crowd skewed results. What is the likeliest cause and what should I check first before telling Emma we're escalating?
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 six events this quarter we repeatedly spend half a day investigating a single low-scoring…
Become — change the pattern
+We keep firefighting low-scoring nights after events
Across six events this quarter we repeatedly spend half a day investigating a single low-scoring session. Most fixes are staffing reassignments that could have been anticipated. Help me see the pattern: where are we losing time and credibility, and what one habit should we change so Emma and I stop redoing the same post-event dig every week?
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.