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 readable brief on discovering new food sources for the R&D meeting tomorrow. Make the…
Execute — do the immediate task
+I need a readable brief on discovering new food sources for the R&D meeting tomorrow. Make the draft agreeable to read: cut jargon, surface the two best candidate ingredients in the first paragraph, and provide one-line rationales linking each candidate to cost, supply risk, and flavor profile.
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 with the beverage technologist and the author, make it easy to approve: put the…
Improve — make it easier to accept
+Before I share this with the beverage technologist and the author, make it easy to approve: put the supply-risk number and estimated cost per kilo up top, make flavor descriptors findable, and flag any sourcing assumptions that would make procurement hesitate.
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 told Priya in R&D that we can source a seaweed concentrate at scale; she replied that her…
Decide — diagnose the stuck moment
+R&D pushed back on a sourcing claim
I just told Priya in R&D that we can source a seaweed concentrate at scale; she replied that her pilot samples didn’t match flavor claims. I’m worried procurement will commit and fail the pilot. I cannot tell Priya how fast suppliers can scale. Is the likely problem my sourcing optimism or a flawed pilot, and what is the best next move to avoid a costly procurement commitment?
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 consistently lose time because new food-source proposals are rejected late by procurement for…
Become — change the pattern
+New-sourcing proposals repeatedly get rejected in procurement
We consistently lose time because new food-source proposals are rejected late by procurement for vague risk reasons. Where are we failing to make sourcing cases persuasive, and what single habit—data to gather or one paragraph to add—would get proposals accepted earlier?
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.