The four heights
The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.
Execute — do the immediate task
+Prepare recommendations on whether to reallocate $400,000 from the R&D budget to the marketing…
Execute — do the immediate task
+Prepare recommendations on whether to reallocate $400,000 from the R&D budget to the marketing campaign starting next quarter. Send the recommendation memo to Priya the head of product and Ravi the VP of Marketing for approval, include a clear bottom-line recommendation, expected ROI over 12 months, and a sensitivity table. Ask for sign-off by Thursday so procurement can update vendor contracts.
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 present to the executive committee, make the recommendation easy to approve—pull the…
Improve — make it easier to accept
+Before I present to the executive committee, make the recommendation easy to approve—pull the one-line expected ROI to the top, show worst/likely/best cases for revenue impact, identify three risks that would make me reverse the reallocation, and flag any contractual or compliance blockers that procurement should review.
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 drafted a proposal to move $400,000 from R&D to marketing; Ravi, VP of Marketing, verbally pushed…
Decide — diagnose the stuck moment
+The VP of Marketing pushed for the reallocation without data.
I drafted a proposal to move $400,000 from R&D to marketing; Ravi, VP of Marketing, verbally pushed this at the last meeting but hasn’t provided performance data. Priya wants numbers. I fear I’ll approve a politically driven shift that hurts long-term product timelines. What is the most likely reality behind Ravi’s push and what minimal tests or numbers should I demand before I recommend approval?
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 several cycles we reallocate budget to loud stakeholders and later regret slower product…
Become — change the pattern
+We keep reallocating budgets on anecdotes, not metrics.
Across several cycles we reallocate budget to loud stakeholders and later regret slower product delivery. I own the recommendation memos. What recurring habit is costing us time and credibility, and what single change to my process will stop reactive reallocation and force a simple data gate before any budget move?
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.
Quantitative AnalystResearch AnalystStrategy AnalystAlgorithmic Trading AnalystPortfolio AnalystQuantitative Analyst Quantalso: Advise on financial matters
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.