The four heights
The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.
Improve — make it easier to accept
+Before we issue this procedure to the lab bench, make it approval-friendly — open with the expected…
Improve — make it easier to accept
+Before we issue this procedure to the lab bench, make it approval-friendly — open with the expected turnaround and sensitivity, move critical reagent concentrations to a boxed callout, add a short checklist for Jamal Khan to tick at each major step, and flag any steps that would force a repeat run so reviewers can see risk at a glance.
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’ve drafted the LC-MS sample prep and specified a 1:50 dilution with formic acid, but I’m unsure…
Decide — diagnose the stuck moment
+I finished drafting the method but worry about the sample prep step.
I’ve drafted the LC-MS sample prep and specified a 1:50 dilution with formic acid, but I’m unsure if that will suppress low-concentration analytes. Elena Park and Jamal Khan have questions and the run is scheduled next Tuesday. What is the likely risk of the current dilution, what’s the best conservative adjustment now, and one sentence to add explaining the change so validation reviewers accept it?
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.