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 send our two-page fundraising case and budget summary to Priya in foundations and to…
Execute — do the immediate task
+I need to send our two-page fundraising case and budget summary to Priya in foundations and to Marcus, our grants director, for signatures by next Friday. Check the budget tabs for any hidden rows or shifted formulas, confirm the award period matches the narrative, and attach the clean PDF before I request signatures in that order.
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 forward the funder packet to Priya in foundations, make it easier for someone who skims to…
Improve — make it easier to accept
+Before I forward the funder packet to Priya in foundations, make it easier for someone who skims to commit. Pull the headline ask and the one-sentence impact onto the first sheet, surface net additional costs and in-kind match in bold, hyperlink the detailed budget lines so a reviewer can jump from the summary to supporting calculations, and flag any assumptions that would make a program officer hesitate.
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 modeled a three-year budget and Priya says the funder expects two years; Marcus wants us to keep…
Decide — diagnose the stuck moment
+I just finished the budget model and Priya asked for the grant period to match the proposal.
I modeled a three-year budget and Priya says the funder expects two years; Marcus wants us to keep the third year as a sustainability estimate but we haven't confirmed partner contributions. I am worried reducing to two years will under-report needed staff time, while keeping three could trigger funder questions. Tell me the likely trade-offs and the best next step to present to Marcus and Priya in one clear recommendation.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+We have two recurring failures before grants go out: multiple people edit budget tabs directly,…
Become — change the pattern
+We keep losing time reconciling different budget versions before submission.
We have two recurring failures before grants go out: multiple people edit budget tabs directly, producing mismatched formulas, and we only reconcile the master file the day before the deadline. Over the last six submissions that cost us rework and at least one late submission. Recommend one habit change and a practical file-control step that would stop this and fit into our current workflow.
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.