Summarize survey findings visually

Summarize survey findings visually — 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
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

+
I have to turn the survey findings into a visual summary for the supervisor by Tuesday. Create the…
I have to turn the survey findings into a visual summary for the supervisor by Tuesday. Create the dashboard showing depth distribution, temperature profile, and three key anomalies, review each chart for correct axis labels and legends, then deliver the workbook and a one-page PNG summary to Elena and Sam with a brief note.

Improve — make it easier to accept

+
Before I send the visual summary to the marine scientist, make it easy to approve: put the headline…
Before I send the visual summary to the marine scientist, make it easy to approve: put the headline finding and one-line implication at the top, ensure the anomaly points are colored and annotated, make pricing or cost-of-follow-up estimates findable, and flag any chart where sample size is under ten that would make a reviewer hesitate.

Decide — diagnose the stuck moment

+
I built the dashboard and one temperature profile point is an extreme outlier that shifts the…

My summary chart shows an outlier that drives the conclusion.

I built the dashboard and one temperature profile point is an extreme outlier that shifts the report's headline. The field tech insists the sensor was fine, but I don't trust that single reading. I can't tell whether to exclude it, annotate it as suspect, or recommend a resurvey. What is the most defensible choice and the wording I should use in the summary to avoid blame if it's wrong?

Become — change the pattern

+
Over multiple projects the team repeatedly lets single anomalous points steer recommendations,…

We let single outliers dictate recommendations too often.

Over multiple projects the team repeatedly lets single anomalous points steer recommendations, costing us credibility when later checks contradict them. Which review habit or acceptance threshold should we adopt so conclusions require more robust evidence before prompting field rework?

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.