Verify scoring calculations

Verify scoring calculations — 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 need to confirm the scoring formulas used in last quarter's evaluation. Recreate the scoring…
I need to confirm the scoring formulas used in last quarter's evaluation. Recreate the scoring sheet with candidate names in column A, raw inputs in B through E, the intermediate weighted scores in F through H, and the final score formula in I. Add conditional formatting to highlight any negative or zero weights and lock the cells that contain the established weight values so reviewers can't edit them by accident.

Improve — make it easier to accept

+
Before I send this to HR for sign-off, make the scoring transparent and hard to misread. Put the…
Before I send this to HR for sign-off, make the scoring transparent and hard to misread. Put the overall score and rank at the top, show the single line that created each candidate's final score, and flag any candidates whose rank would change if a weight shifted by plus or minus five percent. Add comments where I had to guess an input so the reviewer knows to verify.

Decide — diagnose the stuck moment

+
The ranked list shifted and I tracked it to a hidden cell that contained a weight. The actors are…

The final ranking changed after someone altered a hidden cell

The ranked list shifted and I tracked it to a hidden cell that contained a weight. The actors are the hiring manager who asked for a recalculation and an intern who edits spreadsheets for formatting. I'm afraid someone changed weights to favor a candidate and I don't know whether it was malicious or accidental. What is the most likely cause and what immediate evidence should I extract from the workbook to present to HR?

Become — change the pattern

+
Every quarter we get questions about the final scores because formulas or weights have been…

We lose trust because weights and formulas get accidentally changed

Every quarter we get questions about the final scores because formulas or weights have been altered. Recommend a habit that preserves integrity: the one spreadsheet protection or version control step to adopt, where to record approvals, and one daily check the team should do so we stop rework and credibility hits.

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.