The four heights
The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.
Execute — do the immediate task
+Grade the set of 120 multiple-choice and short-answer exam papers for Acting 201 and return results…
Execute — do the immediate task
+Grade the set of 120 multiple-choice and short-answer exam papers for Acting 201 and return results to Nora in academics by Monday noon. Record each student’s raw score, apply the agreed weighting (MC 60%, short answers 40%), calculate class average and standard deviation, and flag any answer keys with more than 20% wrong for possible key errors.
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 release grades to students, make the spreadsheet easy for Nora to review: put the class…
Improve — make it easier to accept
+Before I release grades to students, make the spreadsheet easy for Nora to review: put the class average and the pass threshold at the top, make student totals and letter grades visible in the leftmost columns, highlight any items where a student’s MC score deviates by more than 30 points from their short-answer score, and mark questions where over 20% failed so Nora can consider regrading or a key adjustment.
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
+After grading, six students scored above 85 on multiple choice but under 50 on short answers. I’m…
Decide — diagnose the stuck moment
+A cluster of students had high MC scores but very low short-answer marks.
After grading, six students scored above 85 on multiple choice but under 50 on short answers. I’m worried I misapplied the short-answer rubric or failed to carry a weighting. I can’t tell whether the issue is my rubric, a copying error when applying weights, or students gaming the MC. What is the most likely cause and the quickest verification step so I can correct grades before sending them to Nora?
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 term we spend a day reconciling grades because instructors export scores in different layouts…
Become — change the pattern
+Spending hours reconciling grade sheets every term because of inconsistent weighting and layout.
Every term we spend a day reconciling grades because instructors export scores in different layouts and sometimes forget agreed weightings. Across three courses last year that cost me two full days. What habit and a single standard template or rule should I enforce so importing and computing final grades becomes a five‑minute task instead of a day?
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.
Drama TeacherInstrument TeacherCulinary InstructorSocial Work Lectureralso: Administer and grade examinationsalso: Compile and grade exams
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.