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 I hand this to the accreditation reviewer, make the write-up easy to follow — pull the…
Improve — make it easier to accept
+Before I hand this to the accreditation reviewer, make the write-up easy to follow — pull the pass/fail result and confidence note to the top, bold the critical timings, put kit lot numbers in a small table, call out any deviations in a flagged paragraph, and add a clear line for Maria Ruiz to initial.
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 completed the respiratory swab run and the control behaved but one sample showed a faint…
Decide — diagnose the stuck moment
+I ran the protocol and got an unexpected faint positive.
I completed the respiratory swab run and the control behaved but one sample showed a faint positive; Maria Ruiz and I logged the time and instrument used, but I’m not sure whether to flag it as actionable or repeat the test. Explain the likely causes given the protocol, the next step I should take before recording a final result, and the short text I should add to the report to justify that choice.
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.