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 finished the draft operational-risk register for the ground crew and need it reviewed. Send the…
Execute — do the immediate task
+I finished the draft operational-risk register for the ground crew and need it reviewed. Send the register to Laila in safety and to Darren, the head of operations, for approval Thursday; sign it yourself first after you verify every risk has an owner, last-mitigation date, and an estimated financial impact.
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 this risk spreadsheet to safety, make it easier to approve: surface the top five…
Improve — make it easier to accept
+Before I forward this risk spreadsheet to safety, make it easier to approve: surface the top five high-impact risks at the top, show when each was last tested, flag any risks without a named owner, and mark controls that depend on external vendors or single people so reviewers know reliability concerns immediately.
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 just cataloged a high-severity equipment failure risk with a conservative probability, but Laila…
Decide — diagnose the stuck moment
+I logged a high-severity maintenance risk but safety says it's not urgent; I'm unsure who should act.
I just cataloged a high-severity equipment failure risk with a conservative probability, but Laila in safety downgraded it and says operations can leave it for the next maintenance cycle. I can’t tell if Laila is under-resourcing safety or if my probability estimate is inflated. What is the likely diagnosis, what additional data should I collect quickly, and what is the best immediate step so we neither overreact nor leave a genuine hazard unaddressed?
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 recording near-misses and high risks, yet mitigations stall and no one is accountable…
Become — change the pattern
+Near-misses keep being recorded but mitigations aren't tracked to completion.
We keep recording near-misses and high risks, yet mitigations stall and no one is accountable beyond an initial note. That burns credibility and leaves real exposure. What one habit change around assigning owners, one reporting cadence, and one spreadsheet structure would ensure risks move from identification to resolved without doubling the workload for operations or safety?
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.