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 must deliver the research report and slides for Friday’s departmental seminar. Assemble the…
Execute — do the immediate task
+I must deliver the research report and slides for Friday’s departmental seminar. Assemble the report, the executive summary, and the slide deck, then send them to Dr. Patel and Jessica in communications for a single consolidated review, with a Thursday noon deadline so we can incorporate edits. Verify the bibliography format, that every figure caption cites its source, and that the results section matches the slide headlines before sending.
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 circulating this research report to the funding committee, make it easy for a nontechnical…
Improve — make it easier to accept
+Before circulating this research report to the funding committee, make it easy for a nontechnical reviewer to say yes: lead with the one-sentence takeaway, surface the potential impact and the estimated cost savings on page one, make methods skimmable with a short bullet list, and flag any results that need replication so they don’t mistake uncertainty for weakness.
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
+At the funding meeting the officer asked for an ROI and a deployment timeline for the process I…
Decide — diagnose the stuck moment
+The funding officer asked for an ROI number I don’t have
At the funding meeting the officer asked for an ROI and a deployment timeline for the process I described. Dr. Patel and the head of operations are in my loop; I don’t actually have validated cost numbers and I’m worried overstating savings will kill credibility. What is the best concise response that gives the committee something actionable without fabricating an ROI?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+I keep losing hours reformatting the same research report for different audiences: funders want…
Become — change the pattern
+Each report needs manual reformatting for different reviewers
I keep losing hours reformatting the same research report for different audiences: funders want one-pagers, academics want methods, and communications want images sized for slides. This eats time and leads to errors. Which one drafting habit or template strategy will save time and keep every version accurate and reviewable?
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.
Computational BiologistExperimentation ScientistField BiologistMarine BiologistPharma Formulation ScientistPlanetary Scientistalso: Prepare reports and present findingsalso: Write research papers and reportsalso: Write technical reports and research papers
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.