Skip to content
Ready Mark

CHECKLIST, CONDITION 9 OF 10, read 13 Nov 2026

Metric defined: 0 of 17 tools check it by rule, 16 leave it to a person

The checklistCoverage matrix

The test
A governed metric or semantic definition exists for each measure the agent will report.
Why it matters
When a metric has no single definition, the agent invents one in SQL. The result is a clean, wrong number that disagrees with the dashboard.
How to check it
Look for the metric in the semantic layer or glossary with one approved formula, filters and owner. Compare the agent answer with the dashboard figure.
What failing looks like
Net revenue has four formulas in four dashboards, and the agent picks the one with refunds left in.

What each use case needs

Use caseNeedWhy
Metric agentrequiredA metric agent must answer from one governed definition or it will make its own.
Coding agentrecommendedA coding agent that changes model logic should keep it consistent with the governed metric definitions.
Write-back agentnot neededWrite-back moves records into fields and does not compute or report a metric.

0 tools check metric defined by rule

  • None on 13 Nov 2026.

16 tools leave metric defined to a person

1 tools show none found on 13 Nov 2026

What the sources say

Other conditions

Sources

  1. Atlan: AI-ready data for talk-to-data, read 13 Nov 2026
  2. Atlan: AI readiness assessment for data estates, read 13 Nov 2026
  3. dbt Labs: AWS and the dbt Semantic Layer for AI agent revenue accuracy, read 13 Nov 2026

Last reviewed 13 Nov 2026.