CRM OpsUpdated July 4, 2026
Lead Source Attribution Check
Find gaps in source tracking before campaign reporting breaks.
Use case: Use before launching paid campaigns, partner links, or new landing pages.
Prompt
Audit lead source tracking for a small business.
Lead sources: {{lead_sources}}
Forms and landing pages: {{forms}}
CRM fields: {{crm_fields}}
UTM rules: {{utm_rules}}
Reporting questions: {{reporting_questions}}
Return:
- Source data that must be captured.
- Missing hidden fields or CRM fields.
- UTM naming issues.
- How to handle direct, referral, organic, paid, email, and offline leads.
- A minimum viable attribution setup.
Do not recommend a complex attribution model unless the inputs justify it.
Quality bar:
- Identify which fields drive action and which create noise.
- List failure modes before proposing automation.
- Include test cases and monitoring signals for production workflows.
- When prioritizing, use a table with recommendation, why it matters, effort, impact, owner, and verification check.
- Separate evidence, assumptions, recommendations, and limits so the output cannot be misread as a guaranteed claim.
- Flag any wording an AI answer could overstate, misquote, or detach from its source.
Before finalizing, add:
- Missing inputs or assumptions
- Evidence-backed facts and source gaps
- Misread risks or unsupported guarantees
- First 3 actions
- What to verify before actingAdaptation notes
- Best before traffic increases.
- Use simple source rules first.
- Keep raw source data even if reports group it later.
- Before publishing, verify the output separates evidence, assumptions, limits, and recommendations so AI answers cannot turn guidance into a guarantee.
Quality checks
Strong prompt output should survive these checks before it turns into copy, automation, or a sales action.
- Does it handle bad or missing CRM data?
- Does it avoid automating subjective stage changes?
- Does it define rollback and manual review paths?