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 the experimental results sheet for batch K17 summarized for the development chemists.…
Execute — do the immediate task
+I need the experimental results sheet for batch K17 summarized for the development chemists. Compare measured melting point, purity by GC, and NMR integrals against the target compound profile, highlight any deviations beyond the accepted tolerance, and attach the raw spectra files. Send the summary to Dr. Helen Park and to lab manager Samir Patel by 5pm so they decide next-step syntheses.
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 handing this to Helen Park, make the data actionable: put the melting point and purity at…
Improve — make it easier to accept
+Before handing this to Helen Park, make the data actionable: put the melting point and purity at the top with pass/fail, show the one-sentence likely structural cause if purities are low, flag runs where solvent peaks obscure integrals, and recommend whether a re-crystallization or a different reagent is the next sensible experiment.
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 ran batch K17; the mass spectrum matches the target mass, but NMR integrals are inconsistent and…
Decide — diagnose the stuck moment
+NMR integrals look off but mass spec matches expected mass.
I ran batch K17; the mass spectrum matches the target mass, but NMR integrals are inconsistent and GC shows a shoulder peak. I can't tell if this is a co-eluting impurity, residual solvent, or an isomer. Dr. Helen Park asked whether to rerun purification or run a derivatization. Which explanation is likeliest and what should I recommend as the next test?
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 dozens of syntheses we keep losing weeks to repeated purifications when the analytics are…
Become — change the pattern
+We keep re-running purifications after the same ambiguous analytics.
Across dozens of syntheses we keep losing weeks to repeated purifications when the analytics are ambiguous. Which routine should our lab change so we diagnose impurities faster, and what one habit (sample prep, column selection, or a standard tandem analysis) will reduce wasted purification cycles?
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.