What problem does it solve?
Cold emails often need a "not sure if this is you" referral angle, but naming the wrong colleague — or worse, naming the recipient back to themselves — destroys credibility. This playbook produces a safe, verified other_prospects variable (e.g. "Jeff Barg or Rob Cook") that slots into a referral CTA without ever naming the person being emailed.
Core Features & Use Cases
- Hard recipient exclusion: Filters candidates on normalized first+last name and LinkedIn profile URL before any model call, so the recipient can never appear in their own email; rows missing
recipient_full_name refuse to run.
- AI judge with audit trail: A locked prompt screens provider candidates for seniority, headline contradictions, and support-staff titles, returning both kept names and dropped reasons for cheap QA.
- Still-there verification: A web check confirms each named person is still at the company before the variable ships, since provider job titles go stale.
- Use Case: A campaign targeting VPs of Operations wants a "if this sits with someone else" CTA. The playbook finds two other senior people at each prospect's domain, verifies them, and outputs a ready-to-drop phrase — or an empty string that removes the whole sentence.
Quick Start
Ask Claude to build the other_prospects variable for a lead list using this playbook, providing each row's domain, recipient full name, LinkedIn URL, and persona titles.