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 this climate-initiative evaluation to Marta in sustainability and to Omar in…
Execute — do the immediate task
+I need to send this climate-initiative evaluation to Marta in sustainability and to Omar in strategy for their approval, signers in that order, with a Wednesday deadline. Check the cost-benefit table for missing assumptions, ensure the emissions baselines recalculate from the 2020 sheet, and confirm the sensitivity scenarios include low, medium and high uptake before routing for e-signature.
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 city review team, make the evaluation easy to accept: surface net present…
Improve — make it easier to accept
+Before I send this to the city review team, make the evaluation easy to accept: surface net present value and avoided CO2t on the first sheet, flag any projects that push payback past seven years, and make the funding rows and required permits jump out so a reviewer can say yes or ask one focused question.
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
+The climate team told me to include adaptation benefits; procurement expects hard cost numbers. I…
Decide — diagnose the stuck moment
+I ran the model and net present value turned negative for two projects.
The climate team told me to include adaptation benefits; procurement expects hard cost numbers. I produced a blended NPV and now two projects show negative NPV, but I do not know whether to drop adaptation benefits, extend the horizon, or ask for additional funding. Which is the likely diagnosis and the best next move to present to Marta and Omar this Wednesday?
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 rounds of initiative reviews we spend most time reconciling baseline emissions…
Become — change the pattern
+We keep reworking assumptions and losing credibility when baselines shift mid-review.
Over the last three rounds of initiative reviews we spend most time reconciling baseline emissions and discount rates, then scramble to update every scenario sheet. Where am I consistently losing time and stakeholder trust, and what one habit should I change so future evaluations require one fewer full recalculation cycle?
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.