Types of metal

Types of metal — real work, not an imagined feature: named inside 4 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.

4career 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 list of metal samples with measured densities, hardness numbers and magnetic tests.…
I have a list of metal samples with measured densities, hardness numbers and magnetic tests. Prepare a clean sheet that sorts each sample by likely metal type, highlights any that contradict more than one test, and adds a confidence column I can defend in the lab report. I need it by Wednesday so I can include it in the client handoff.

Improve — make it easier to accept

+
Before I send the metal-identification table to procurement, make it quick for a non-technical…
Before I send the metal-identification table to procurement, make it quick for a non-technical buyer to approve. Put the most likely metal name and its primary evidence on the left, expose the one test that could make a reviewer hesitate, and summarize how many samples need confirmatory testing and why.

Decide — diagnose the stuck moment

+
I ran density, hardness and a magnetism check on 28 metal fragments and two samples show density…

I ran three tests and they disagree on two samples

I ran density, hardness and a magnetism check on 28 metal fragments and two samples show density consistent with aluminum but are magnetic and have hardness like steel. Procurement expects a single metal label. Tell me the most likely diagnoses, which quick follow-up test to run in the lab this afternoon, and what to tell procurement now so I don’t lose credibility.

Become — change the pattern

+
Across dozens of batches we repeatedly spend time re-testing 6–8 ambiguous fragments that force…

We keep re-testing a small set of ambiguous samples

Across dozens of batches we repeatedly spend time re-testing 6–8 ambiguous fragments that force weekend lab runs. Where are we most likely wasting time in our identification workflow, what simple habit would cut re-tests by half, and how should I change the sample arrival checklist to reduce these recurring ambiguities?

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.