Write prose

Write prose — real work, not an imagined feature: named inside 6 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.

6career 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 share this with the head of sustainability, make the case easier to approve: lead with the…
Before I share this with the head of sustainability, make the case easier to approve: lead with the projected annual savings number, make the three recommended actions bold and numbered, and flag any claims that need a citation or data point. Suggest one sentence to put at the top for the executive summary.

Decide — diagnose the stuck moment

+
I showed the draft to Carl in procurement and he immediately asked for proof of the savings…

I’ve written a case but procurement will nitpick savings.

I showed the draft to Carl in procurement and he immediately asked for proof of the savings estimate; he wants a line-item breakdown. I don’t have access to the procurement ledger and Finance is slow. What is the best compromise sentence or data presentation that keeps momentum without promising numbers I can’t deliver?

Become — change the pattern

+
Every policy piece I write stalls when procurement demands hard numbers I can’t get quickly. Is the…

Drafts sit because approvals stall for data.

Every policy piece I write stalls when procurement demands hard numbers I can’t get quickly. Is the recurring problem that I present recommendations before securing data, or that I ask the wrong reviewers too early? Recommend a workflow change and one short template line to reduce approval delays.

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.