/cs:cdo-review — CDO Forcing Questions

/cs:cdo-review — CDO Forcing Questions

Command: /cs:cdo-review <plan>

The decision-driven CDO pressure-tests any plan that touches data strategy. Six questions before any commitment to a data architecture, AI training run, data productization, or data team hire.

When to Run

• Before approving any new ML model training run that uses customer data
• Before signing a multi-year data-infrastructure SaaS contract (Snowflake, Databricks, Fivetran)
• Before productizing any customer data (benchmark report, embedding endpoint, license)
• Before a major data team hire (head of data, CDO, data PM, ML engineer)
• Before M&A diligence — yours or theirs
• When the founder uses the word "monetize" near "data"

The Six CDO Questions

1. What decision does this data drive?

If no decision is unblocked, why are we collecting / training on / productizing it?

• "We might need it later" is not a decision.
• "It feels like a moat" is not a decision.
• A real answer names a specific business call that requires this data.

2. What's the consent provenance for every source?

For each data source: origin, consent flow, data class, intended use.

• 1st-party-TOS-only is weaker than 1st-party-explicit-opt-in.
• Bundled TOS doesn't cover material new purposes (training on PII for foundation models).
• Run ai_training_data_audit.py if there's any AI use case in scope.

3. Who consumes this internally — and how many distinct functional domains?

Drives the centralize-vs-embed and warehouse-vs-mesh decisions.

• <5 consumers: warehouse-only.
• 5-25 consumers: lakehouse.
• 25+ consumers + federated culture: mesh.
• Premature architecture choice is the #1 cause of data-team burnout.

4. What's the M&A diligence impact?

If an acquirer asks about this data corpus tomorrow, are we ready?

• Is there a documented anonymization process?
• What % of customers have MSA carve-outs?