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 an analysis-ready workbook that tracks condition scores, repair priorities and funding gaps…
Execute — do the immediate task
+I need an analysis-ready workbook that tracks condition scores, repair priorities and funding gaps for the old stone bridge so the preservation board can allocate the next tranche. Create a ranked condition table, show the cost to bring each element to acceptable condition, and compute the total funding shortfall. Include a checklist of reports and photos I must attach before the board meeting on Thursday.
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 send this preservation support pack to the architect and the board, make the evidence easy…
Improve — make it easier to accept
+Before I send this preservation support pack to the architect and the board, make the evidence easy to verify: flag any elements whose condition score depends on a single inspection, surface assumptions about material longevity, and add a two-line note on how to validate each high-cost item quickly in the field.
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 turned inspection notes into a condition table and put a repair cost on the parapet; the…
Decide — diagnose the stuck moment
+The architect questioned a high cost tied to the bridge parapet condition score.
I turned inspection notes into a condition table and put a repair cost on the parapet; the architect says my condition score is too high but won't say whether based on different inspection criteria or new photos. What's the most likely cause and what quick field check or document should I ask for to settle it before the funding decision?
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 five preservation studies we lose credibility because inspectors score condition differently…
Become — change the pattern
+My preservation analyses get challenged because condition scoring is inconsistent across inspectors.
Across five preservation studies we lose credibility because inspectors score condition differently and estimates swing. What habit change will standardize scoring and restore trust? Propose a one-page scoring rubric, who trains new inspectors, and a quick spreadsheet test to spot outlier scores at delivery.
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.