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 to circulate my grant-review spreadsheet to the panel by Wednesday. Confirm every…
Execute — do the immediate task
+I need to circulate my grant-review spreadsheet to the panel by Wednesday. Confirm every application row has reviewer scores, letters of support linked, conflict declarations filled, and that the ranking tab recalculates in the order of weighted score before I share it with Dr. Alvarez and the selection committee.
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 send this to the review panel, make it easy for them to decide: surface the composite…
Improve — make it easier to accept
+Before I send this to the review panel, make it easy for them to decide: surface the composite score and funding recommendation in the leftmost columns, flag any application missing budget justification or institutional approval, collapse reviewer comments into a single summary cell, and mark the threshold candidates for discussion.
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 finished entering scores but two reviewers rated the same proposal 2 and 9; the selection…
Decide — diagnose the stuck moment
+Two reviewers gave wildly different scores and panel asks why.
I finished entering scores but two reviewers rated the same proposal 2 and 9; the selection committee emailed asking for reconciliation and we meet Friday. I can’t tell if one reviewer used a different rubric, mis-clicked, or if there’s a data-entry error. What’s the most likely explanation and the fastest way to present a defensible note to the committee?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+Every funding round we waste a day reconciling divergent reviewer scores because reviewers use ad…
Become — change the pattern
+Recurring messy score reconciliations slowing final decisions
Every funding round we waste a day reconciling divergent reviewer scores because reviewers use ad hoc rubrics or enter scores into different tabs. Across six rounds the pattern is inconsistent score scales and missing justifications. Which concrete change should I make to the review workbook and reviewer instructions so panels stop getting stuck and decisions close two days 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.