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 a test log for an object from the archive: item 2021.07, a bound ledger with insect webbing.…
Execute — do the immediate task
+I need a test log for an object from the archive: item 2021.07, a bound ledger with insect webbing. Spell out the physical tests to run in order—light table transillumination, tensile sampling of sewing thread, pH swab of paper—who does each test, sample sizes, and acceptable pass/fail criteria, plus a Friday deadline for preliminary findings.
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 circulate the conservation tests to the curator, make the report easier to act on: put the…
Improve — make it easier to accept
+Before I circulate the conservation tests to the curator, make the report easier to act on: put the key risk (acidic media or insect activity) at the top, list tests that change handling or storage immediately, make the likely conservation intervention visible, and flag any tests that require owner approval or destructive sampling.
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’m the artifact conservator preparing to sample sewing thread from ledger 2021.07; the curator…
Decide — diagnose the stuck moment
+Curator refuses destructive sampling for a thread test
I’m the artifact conservator preparing to sample sewing thread from ledger 2021.07; the curator just refused any destructive sampling but needs a diagnosis of binding failure. I can’t tell if non-destructive imaging will be sufficient. What’s the most likely tradeoff and the best next move that preserves the object yet gives us a usable answer?
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 the collection we keep ordering small, slow physical tests that rarely change treatment…
Become — change the pattern
+We run too many low-value tests
Across the collection we keep ordering small, slow physical tests that rarely change treatment decisions and eat our budget. I want to stop low-value sampling and focus lab time where it matters. What routine or decision rule would you adopt to cut at least half of these tests without raising risk?
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.