# Twelve questions tell you how ready one asset is and what to fix first

SELF-CHECK, read 13 Nov 2026

**The short answer.** Answer twelve questions about one table, metric or dashboard: yes scores 2, partly 1, no 0, for a total of 24. The levels are Not ready (0 to 6), Early (7 to 13), Nearly ready (14 to 19), Ready (20 to 24). The page works as a printed list, and nothing you enter is stored or sent.

Pick one asset: a table, a metric or a dashboard that you plan to give to an agent. Answer each question for that asset only, then read the level and the first fixes.

The page is a plain form. Printed, it is a worksheet. With JavaScript on, a small script adds the answers in your browser and names the level; it does not store the answers and does not send them anywhere.

1. Does this asset have a named person or team recorded as its owner who still answers messages? (yes 2, partly 1, no 0). If not yes: Find the owner in the catalog and confirm they respond, or assign one this week.
2. Does the asset and each column the agent will use have a plain business description? (yes 2, partly 1, no 0). If not yes: Write short descriptions for the columns the agent will touch before anything else.
3. Is the asset marked certified, endorsed or verified by someone with authority? (yes 2, partly 1, no 0). If not yes: Have the owner review the asset and set its status before the agent uses it.
4. Do quality tests run on the asset and are they passing today? (yes 2, partly 1, no 0). If not yes: Add tests for keys, nulls and row counts and fix any that fail.
5. Is the asset updated within the freshness window your use expects, and is that window written down? (yes 2, partly 1, no 0). If not yes: Write down the expected freshness and add an alert for late loads.
6. Is sensitive data classified, with PII columns flagged or the asset confirmed PII-free? (yes 2, partly 1, no 0). If not yes: Run a classification scan and tag the PII columns.
7. Can you trace the asset back to its sources, down to the key columns? (yes 2, partly 1, no 0). If not yes: Connect the missing lineage hops, starting with the columns the agent reads.
8. Is the asset in active use and not marked deprecated? (yes 2, partly 1, no 0). If not yes: Check the deprecated flag and recent queries, and point the agent at the live replacement.
9. Does each metric the agent will report have one governed definition? (yes 2, partly 1, no 0). If not yes: Pick one approved formula for each metric and record it in the semantic layer.
10. Does an access policy say this agent may use the asset for this purpose? (yes 2, partly 1, no 0). If not yes: Write the policy and give the agent its own limited account.
11. If the agent writes back, is each write target approved, limited and reversible? (yes 2, partly 1, no 0). If not yes: Limit write access to one approved target and add a way to undo changes.
12. If the agent edits models, can it see what sits downstream and who reviews its changes? (yes 2, partly 1, no 0). If not yes: Turn on lineage for the project and require an owner review on every pull request.

Scoring: yes=2, partly=1, no=0, max 24.

## The levels

| Level | Score | What it means |
| --- | --- | --- |
| Not ready | 0 to 6 | Most basics are missing, so keep agents away from this data for now. |
| Early | 7 to 13 | Some basics are in place, so limit the agent to read-only help on a few assets. |
| Nearly ready | 14 to 19 | Most conditions hold, so fix the remaining gaps before you allow wider use or writes. |
| Ready | 20 to 24 | The asset meets nearly every condition and is fit for the use you checked. |

## What the questions map to

| Question | Conditions |
| --- | --- |
| 1. Does this asset have a named person or team recorded as its owner who still answers messages? | [Named owner](/checklist/owner/) |
| 2. Does the asset and each column the agent will use have a plain business description? | [Documented](/checklist/documented/) |
| 3. Is the asset marked certified, endorsed or verified by someone with authority? | [Certified](/checklist/certified/) |
| 4. Do quality tests run on the asset and are they passing today? | [Quality tests pass](/checklist/quality/) |
| 5. Is the asset updated within the freshness window your use expects, and is that window written down? | [Fresh](/checklist/fresh/) |
| 6. Is sensitive data classified, with PII columns flagged or the asset confirmed PII-free? | [Sensitivity classified](/checklist/sensitivity/) |
| 7. Can you trace the asset back to its sources, down to the key columns? | [Lineage known](/checklist/lineage/) |
| 8. Is the asset in active use and not marked deprecated? | [Active use](/checklist/usage/) |
| 9. Does each metric the agent will report have one governed definition? | [Metric defined](/checklist/metric_definition/) |
| 10. Does an access policy say this agent may use the asset for this purpose? | [Access policy allows AI use](/checklist/access/) |
| 11. If the agent writes back, is each write target approved, limited and reversible? | [Access policy allows AI use](/checklist/access/), [Named owner](/checklist/owner/), [Quality tests pass](/checklist/quality/) |
| 12. If the agent edits models, can it see what sits downstream and who reviews its changes? | [Lineage known](/checklist/lineage/), [Named owner](/checklist/owner/), [Documented](/checklist/documented/) |

## Sources

- Atlan: How to assign owners and stewards for AI-ready data: https://atlan.com/know/ai-agent/ai-ready-data/ai-ready-data-owners-and-stewards/ (read 13 Nov 2026)
- Qlik: The Essentials of AI-Ready Data: https://www.qlik.com/us/resources/topics/ai-ready-data (read 13 Nov 2026)
- Atlan: AI-ready data for talk-to-data: https://atlan.com/know/ai-agent/ai-ready-data/ai-ready-data-for-talk-to-data/ (read 13 Nov 2026)
- dbt Labs: 5 dbt MCP server patterns that work in production: https://www.getdbt.com/blog/5-dbt-mcp-server-patterns-that-work-in-production (read 13 Nov 2026)
- Gartner: Lack of AI-Ready Data Puts AI Projects at Risk (Q&A with Roxane Edjlali, Feb 26, 2025; archived copy): https://web.archive.org/web/2025/https://www.gartner.com/en/newsroom/press-releases/2025-02-26-lack-of-ai-ready-data-puts-ai-projects-at-risk (read 13 Nov 2026)
- McKinsey: A data leader's technical guide to scaling gen AI (archived copy; mckinsey.com did not load from this run): http://web.archive.org/web/20250824123210/https://www.mckinsey.com/capabilities/mckinsey-digital/our-insights/a-data-leaders-technical-guide-to-scaling-gen-ai (read 13 Nov 2026)

Last reviewed 13 Nov 2026. Canonical: https://aireadydatacheck.com/self-check/
