The four heights
The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.
Execute — do the immediate task
+We need to build the prototype compound formulation tracker for Dr. Singh's new battery…
Execute — do the immediate task
+We need to build the prototype compound formulation tracker for Dr. Singh's new battery electrolyte. Take the experiment log, enter ingredient weights and molarities, compute yields and purity percentages per run, add a column calculating batch-scale equivalents for a 10‑liter trial, and flag any run with purity under 95% in orange so the chemists can review before the synthesis meeting on Monday.
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 hand the compound tracker to the lab team, make it actionable. Put the latest average…
Improve — make it easier to accept
+Before I hand the compound tracker to the lab team, make it actionable. Put the latest average purity and yield at the top, make the scaling factors for a 10‑liter batch prominent, call out which reagents drive cost per gram, and list three conditions that correlate with low purity so a chemist can test them quickly.
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 added solvent volume to the sheet and suddenly several purity columns shifted into nonsensical…
Decide — diagnose the stuck moment
+After I added a new column for solvent volume the purity calculations changed.
I added solvent volume to the sheet and suddenly several purity columns shifted into nonsensical percentages. The raw weights are unchanged but the calculated purities no longer match the lab notebook. I suspect I broke a formula reference or the scaling cell was moved. What is the most likely diagnosis and the step-by-step recovery I should run so I can restore accurate purity calculations without redoing every run manually?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+Across projects we repeatedly lose time because someone adds a column for a new parameter and it…
Become — change the pattern
+Scaling calculations and manual edits keep introducing errors across batches.
Across projects we repeatedly lose time because someone adds a column for a new parameter and it corrupts downstream scaling and purity formulas. Which habits and a minimal workbook structure will prevent these errors, make adding new parameters safe, and keep our batch-scale conversions reliable?
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.
Agricultural ChemistAnalytical ChemistCosmetic ChemistEnvironmental ChemistInorganic ChemistMedicinal Chemistalso: Design and develop new products and materialsalso: Develop new products and update existing products
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.