Support data collection and reporting

Support data collection and reporting — real work, not an imagined feature: named inside 5 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.

5career 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

+
Draft a one-page technical appendix that lists the 12 data fields we collected in the coastal…
Draft a one-page technical appendix that lists the 12 data fields we collected in the coastal survey, explains each field's format and acceptable ranges, and notes the responsible collector and submission deadline. Make it clear which fields are mandatory for the quarterly report and which are optional for follow-up.

Improve — make it easier to accept

+
Before I circulate this to the monitoring team, make it easier for data clerks to follow: put…
Before I circulate this to the monitoring team, make it easier for data clerks to follow: put mandatory fields in a table with examples of valid values, move the submission checklist to the first page, surface the most common validation errors, and flag any field descriptions that could be misinterpreted by respondents.

Decide — diagnose the stuck moment

+
We received the coastal dataset and the validator rejected 40 percent because collectors logged…

Our last batch failed validation with missing GPS precision

We received the coastal dataset and the validator rejected 40 percent because collectors logged coordinates without decimal places. The field team says devices round by default. I don't know whether to ask for a re-collect, accept and adjust coordinates, or change validation rules. What's the likely best move that preserves data integrity and relationships with field teams?

Become — change the pattern

+
Across five surveys I lose time reconciling formats, chasing missing fields, and rewriting…

We keep getting late, inconsistent datasets from field teams

Across five surveys I lose time reconciling formats, chasing missing fields, and rewriting validators. It costs our analysts a week per quarter. Where should I change habits: the data specification, the collection training, or the submission enforcement? Recommend one concrete habit to adopt and how to test it in the next round.

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.