Perform tests on weapons or substances

Perform tests on weapons or substances — real work, not an imagined feature: named inside 8 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.

8career 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 to prepare the weapons test log and results summary for the lab review tomorrow. Combine the…
I have to prepare the weapons test log and results summary for the lab review tomorrow. Combine the test runs, specimen IDs, operator initials, and force measurements into one sheet, confirm units are consistent, and highlight any runs with values outside the expected ballistic range. Send the compiled file to Dr. Morales for technical sign-off first and then to Compliance for the record.

Improve — make it easier to accept

+
Before I hand the test log to Dr. Morales, make it straightforward to judge failures: put a…
Before I hand the test log to Dr. Morales, make it straightforward to judge failures: put a top-line summary of runs passing and failing, show the three parameters most likely to indicate contamination, convert all measurements to the same units, and flag any missing operator initials or chain-of-custody notes that would make a reviewer hesitate.

Decide — diagnose the stuck moment

+
I merged yesterday’s test outputs and one run shows a velocity spike beyond historical range; Dr.…

A test run returned an unexpected high velocity but chain-of-custody is incomplete.

I merged yesterday’s test outputs and one run shows a velocity spike beyond historical range; Dr. Morales will suspect instrument drift and Compliance will worry about procedure. The chain-of-custody has a missing signature for that specimen. I don’t know if the spike is real, an input/transcription error, or due to the missing signature. What’s the likely diagnosis and the two immediate steps I should take to preserve evidence and resolve the result?

Become — change the pattern

+
Across multiple test cycles we lose time reconciling units, missing operator initials, and…

We repeatedly chase missing operator initials and inconsistent units across tests.

Across multiple test cycles we lose time reconciling units, missing operator initials, and inconsistent specimen IDs; it causes rework and question from Compliance. Which two habits or small procedural fixes will reduce these recurring data problems and how should I roll them out in the lab for the next testing batch?

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.