Lead ResponseUpdated July 4, 2026
Negative-Intent Lead Filter
Spot leads that should be routed to nurture, support, or no follow-up.
Use case: Use to reduce wasted sales time without adding a public quiz.
Prompt
Classify this lead using fit and negative-intent signals.
Lead text: {{lead_text}}
Source: {{source}}
Fit rules: {{fit_rules}}
Disqualifiers: {{disqualifiers}}
Return:
- Recommended route: sales, nurture, support, partner, or no follow-up.
- Positive fit signals.
- Negative fit signals.
- Missing data that would change the decision.
- Suggested response if the lead is not a fit.
Be conservative. Do not reject a lead only because the message is short.
Quality bar:
- Classify buying intent and missing data separately.
- Recommend one next action, not a menu of vague options.
- Keep customer-facing copy short and easy to approve.
- 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
- Use internally, not as a public-facing rejection system.
- Review edge cases manually.
- Good replacement for a heavy qualification quiz.
- 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 avoid adding friction to hot leads?
- Does it preserve consent and contact-channel boundaries?
- Does it give a route the CRM can actually store?