Prepare reports of activities, evaluations, recommendations, or decisions.

Prepare reports of activities, evaluations, recommendations, or decisions. — real work, not an imagined feature: named inside 7 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.

7career 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 need a clean monthly activity report for the medical examiner office that shows number of exams,…
I need a clean monthly activity report for the medical examiner office that shows number of exams, pass/fail counts, and recommendations. Send the attached workbook to Priya in payroll and to James in clinical oversight for e-signature, signers in that order, with a Friday deadline—check totals and the month filter are correct first.

Improve — make it easier to accept

+
Before I send this to the clinic director, make the report easy to scan: put total exams, pass…
Before I send this to the clinic director, make the report easy to scan: put total exams, pass rate, and key recommendations at the top, make counts by exam type clickable, and flag any week where follow-ups exceed three. Keep the print layout to one page.

Decide — diagnose the stuck moment

+
I just updated the March sheet and noticed the pass rate dropped from 87% to 72% after importing a…

I opened March numbers and the pass rate dropped sharply.

I just updated the March sheet and noticed the pass rate dropped from 87% to 72% after importing a lab file. Priya in payroll needs to sign the monthly approval tomorrow; James will push changes to clinical notes. I’m afraid the drop is a data-import mismatch but can’t prove it quickly. Do I freeze the report and ask for an urgent data reconciliation, or send the lower number with a caveat and promise a corrected version later?

Become — change the pattern

+
Every month we finish the activity report, get it signed, then catch data errors that force a…

We keep sending corrections after monthly sign-off.

Every month we finish the activity report, get it signed, then catch data errors that force a correction and damage credibility. Across nine months most corrections come from mismatched import templates and missing week filters. What routine change will prevent post-signature fixes and make signers trust the first version?

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.