Microsoft Word

Microsoft Word — real work, not an imagined feature: named in real job descriptions. 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.

1prompt heights

The four heights

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

Decide — diagnose the stuck moment

+
I merged tracked changes from Maria, Thomas, and Chris into the contract; the clause numbering now…

I just merged edits from three reviewers and the clause numbers are inconsistent.

I merged tracked changes from Maria, Thomas, and Chris into the contract; the clause numbering now shows duplicates and the table of contents is wrong. I’m worried sending this as is will confuse the signers and delay approval. I cannot tell which edits Thomas intended to replace and which were comments. What is the fastest, lowest‑risk next move to restore a clean, reviewable document before Friday’s sign‑off?

Where the evidence lives

Who was seen doing this, and what people really ask.

also: Word processing
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.

Work Atlasthe whole map, interactiveCareers1,949 jobs and their real tasksSoft skillsthe human part of the workActivities500 things people doPrompt Librarybrowse every prompt