Adjust survey design for practicality

Adjust survey design for practicality — 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
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

+
Send the revised survey instrument and the feasibility notes to Dr. Alvarez and to the field…
Send the revised survey instrument and the feasibility notes to Dr. Alvarez and to the field manager Rosa for approval by Tuesday. Verify skipped logic works across sheets, ensure question numbering matches the consent form, and save a clean copy for deployment.

Improve — make it easier to accept

+
Before I hand this survey to the field team, make it practical for enumerators. Put routing rules…
Before I hand this survey to the field team, make it practical for enumerators. Put routing rules at the top of each sheet, make the expected answer formats explicit next to each question, highlight any items requiring supervisor approval, and flag questions likely to slow interviews so we can drop or reword them.

Decide — diagnose the stuck moment

+
I removed five items to reduce the duration but Rosa estimates interviews will still run 25…

I shortened the questionnaire but the field manager says interview time still looks too long.

I removed five items to reduce the duration but Rosa estimates interviews will still run 25 minutes, risking respondent fatigue. I don't know which questions produce the most value versus time cost. Recommend how to evaluate and which question types to cut or reword so field time drops under 20 minutes without destroying core measures.

Become — change the pattern

+
After three rounds of piloting, enumerators report the same three questions are misunderstood or…

We repeatedly learn in the field that some questions are unanswerable or misinterpreted.

After three rounds of piloting, enumerators report the same three questions are misunderstood or skipped, and we keep patching them ad hoc. Recommend one habit change and a concrete spreadsheet practice for designing and tracking question performance so those problems stop recurring before piloting.

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.