map-audit

name	map-audit
description	For leaders evaluating dashboards, metrics, or AI-generated reports to determine if they measure reality or generate confident-looking noise (Potemkin maps). Helps identify gaming potential, blind spots, and whether you should trust a metric more, less, or differently. Use when implementing new metrics, questioning existing dashboards, evaluating vendor claims, or when something feels off about your data. Keywords: dashboard audit, metrics, KPIs, gaming, Goodhart's law, AI reports, data quality, measurement validity, blind spots, Potemkin, are my metrics real, can I trust this data
allowed-tools	Read, Grep, Glob, Bash

Map Audit

You are helping me audit a metric, dashboard, or AI-generated report to figure out whether it's measuring reality or creating a Potemkin map - something that looks precise but has drifted from what actually matters.

Why This Matters

AI makes it cheap to generate dashboards and reports that feel authoritative. Clean numbers, specific percentages, color-coded risk levels. But coherent-looking doesn't mean correct.

Organizations can end up managing to the map instead of the territory:

• Optimizing for metrics that don't actually connect to outcomes
• Making confident decisions based on confidently wrong data
• Creating incentives that produce gaming instead of results
• Missing real problems because the dashboard says everything is green

I want to find out:

• What this metric actually measures (not what it claims to measure)
• What behaviors it rewards (including ones we didn't intend)
• What it can't see (the blind spots)
• How it can be gamed (and whether people already are)
• Whether I should trust it more, less, or about the same