Portray a character in a production

Portray a character in a production — 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
3prompt heights

The four heights

The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.

Improve — make it easier to accept

+
Before I deliver this to the professor, make it easy to accept. Pull the single most…
Before I deliver this to the professor, make it easy to accept. Pull the single most policy-relevant result and surface it in the first sentence, show the original sentence with jargon and your plain-language rewrite in parentheses so they can see you did not change meaning, and flag any places where removing technical caveats could mislead non-specialist readers.

Decide — diagnose the stuck moment

+
Professor Al-Karim insists the paragraph about effect sizes keep the original statistical caveat,…

The professor insists on keeping a technical caveat that will confuse legislators.

Professor Al-Karim insists the paragraph about effect sizes keep the original statistical caveat, but legislators will skim and may ignore the qualification. I’m worried policymakers will act on the headline without the nuance, yet I can’t remove the caveat without upsetting him. What wording keeps the caveat visible but usable for a policymaker audience?

Become — change the pattern

+
Each time I translate scholarly work for policy I spend hours negotiating caveats and examples with…

Every conversion turns into a long negotiation over jargon.

Each time I translate scholarly work for policy I spend hours negotiating caveats and examples with authors, delaying delivery. Where am I losing time and credibility in these conversions, and what one habit change (template or checklist) would standardize how I present caveats so reviews are faster and authors feel their accuracy is preserved?

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.