Collaborate with engineers and scientists

Collaborate with engineers and scientists — real work, not an imagined feature: named inside 9 evidenced career tasks. Below are four ready AI prompts for it, one per height of help: do it, make it easier to accept, decide when you are stuck, and change the pattern for good.

9career tasks name it
4prompt heights

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 have a three-page methods summary and two figures that need to go to Dr. Ananya Rao in Chemical…
I have a three-page methods summary and two figures that need to go to Dr. Ananya Rao in Chemical Engineering and to Marcus Lee in Field Trials for e-signature by Tuesday midday. Before sending, check the summary reads as a single voice, that the figure captions identify units and sample sizes, and that the legend explains every colored line. Assemble the files into one document in the order: summary, figures, raw-data table, then send to Ananya first, Marcus second.

Improve — make it easier to accept

+
Before I send this methods draft to the lab team, make it easier for engineers to act on. Put the…
Before I send this methods draft to the lab team, make it easier for engineers to act on. Put the key change they must test in the first paragraph, list exact reagent grades and concentrations under a short header, move the measurement tolerances and instrument settings into a one-page checklist, and highlight any assumptions about environmental conditions that could make a protocol fail.

Decide — diagnose the stuck moment

+
I just got edits from Ananya removing the calibration paragraph; she says it’s redundant but I’m…

Ananya returned edits that deleted our calibration step.

I just got edits from Ananya removing the calibration paragraph; she says it’s redundant but I’m not sure she tested under field humidity. Who else reads this, what am I worried they’ll miss, and should I push back and ask for a short experimental note proving calibration wasn’t needed before I accept her change?

Become — change the pattern

+
Across projects we burn time redrawing figures and re-running units checks the night before…

We keep reworking figures at the last minute and missing the field-team details.

Across projects we burn time redrawing figures and re-running units checks the night before reviews. It costs credibility with Marcus and delays trials. What habit should I change in how we assemble drafts so figures and units are final two days before signatures and the field team can flag mismatches early?

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.