Create new artificial substances and useful processes

Create new artificial substances and useful processes — real work, not an imagined feature: named inside 5 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.

5career 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 lab‑scale formulation log and a list of candidate reagents with test results. Send the…
I have a lab‑scale formulation log and a list of candidate reagents with test results. Send the attached process-development summary to Dr. Singh in R&D and to finance for preliminary capex approval, with a Wednesday deadline — signers in that order. Confirm safety data sheets are attached and that any regulatory flags are noted before sending.

Improve — make it easier to accept

+
Before I send this to R&D and finance, make their review easy: pull the top-performing candidates…
Before I send this to R&D and finance, make their review easy: pull the top-performing candidates into one table with yield, purity, and scale‑up risk column up front, show an estimated timeline and resource needs, and highlight any steps that need pilot permits so reviewers can approve or ask one focused question.

Decide — diagnose the stuck moment

+
I ran three pilot runs and yields dropped by half when scaled. Dr. Singh will ask for root cause…

Pilot trials failed to scale yields and finance is pushing back.

I ran three pilot runs and yields dropped by half when scaled. Dr. Singh will ask for root cause and finance will question further capex. I don’t know whether the loss is due to batch heating or reactant purity. What’s the likely diagnosis given the pattern, and what immediate tests or data should I provide so R&D and finance can decide whether to continue next Wednesday?

Become — change the pattern

+
Across multiple projects we waste time because pilot reports list raw runs but never summarize…

Scale‑up requests keep getting rejected because pilot data aren’t summarized clearly for finance.

Across multiple projects we waste time because pilot reports list raw runs but never summarize expected cost per kilogram at scale or regulatory hold points. I lose funding and momentum. Which three reporting habits should I change — in summarizing yields, listing regulatory risks, and projecting capex — so scale‑up proposals get approved faster?

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.