The four heights
The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.
Execute — do the immediate task
+Produce the dossier for the biology specialization review: gather the latest experimental results,…
Execute — do the immediate task
+Produce the dossier for the biology specialization review: gather the latest experimental results, protocol deviations, and lab notebook summaries for my subfield, list the key unanswered questions and three candidate papers to cite, and prepare a two-paragraph cover note for the department head summarizing why this specialty needs sustained support next quarter.
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 this specialization packet to the faculty committee, make it easy to assess:…
Improve — make it easier to accept
+Before I circulate this specialization packet to the faculty committee, make it easy to assess: surface the primary contribution in one sentence, present the evidence that differentiates our approach from competing labs, highlight the resource gaps that would block progress, and flag any data quality issues that would give committee members pause.
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 got a reviewer comment saying our methods overlap with a rival lab and they doubt novelty.…
Decide — diagnose the stuck moment
+My grant reviewer questioned whether my subfield work is novel
I just got a reviewer comment saying our methods overlap with a rival lab and they doubt novelty. The department head and the grant committee will read my rebuttal; I don't know if the overlap is substantive, whether I can point to different endpoints, or if I need to adjust the proposal. What is the most credible way to diagnose novelty quickly and what should I put in the rebuttal to preserve funding chances?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+Over the last three cycles our proposals in this specialization are being outcompeted on perceived…
Become — change the pattern
+We keep losing small grants to similar labs
Over the last three cycles our proposals in this specialization are being outcompeted on perceived novelty and clarity. The recurring losses cost momentum and graduate recruitment. Which one habit should we change — improve framing of novelty in the first paragraph, add a direct method comparison table, or pre-submit a one-page pitch to trusted peers — to shift outcomes fastest? Suggest the single action and how to trial it.
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.