Best for
- Agencies prospecting businesses already investing in acquisition
- B2B service teams using observable operational triggers
- Outbound programs that need a timely reason to contact founders
Find ICP companies currently running ads, verify founder or owner context, develop one evidence-bounded outreach hypothesis, choose email or manual LinkedIn, activate safely, and measure whether the signal is useful.
A governed prospecting engine with live-ad evidence, verified founders and contacts, compliant channel routing, reviewed messages, idempotent activation, reply handling, and signal-quality reporting.
Quick view
Check the audience, core tools, and access before you start the detailed steps.
Best for
Core tools
4 tools used across the workflow.
Access
Preview the open steps, then unlock the remaining implementation details and prompts.
Why this works
Active advertising can indicate a company is working on acquisition now, but it does not prove performance, spend, or need. This workflow preserves the ad as a sourced timing signal, verifies the decision-maker and contact, and requires a separate service-relevant hypothesis before outreach. Channel, suppression, freshness, and platform rules remain explicit so the system does not turn public context into invasive automation.
Expected results
Research production
8-14 hours saved per batch
Structured ad capture, enrichment, channel rules, drafting, and activation replace repeated manual research and setup.
Context quality
Every message linked to a live ad observation
Ad URLs, dates, explicit text, founder evidence, and proof remain available for human verification.
Outreach safety
Suppression and jurisdiction rechecked before activation
Eligible records are revalidated, LinkedIn remains manual, and duplicate channel actions are blocked.
Signal learning
Ad themes and hypotheses measured
The scorecard evaluates whether the trigger and service connection produce qualified conversations, not just opens.
Step-by-step workflow
The first 2 steps are open. Pro unlocks the remaining steps, copy-paste prompts, pro tips, tool-by-tool setup guidance, and implementation details.
60-90 min
60-90 min
Define the company size, industry, geography, offer fit, advertising channel, minimum ad activity, founder or owner role, and exclusions for the prospecting system. Set outreach jurisdiction rules, consent or legitimate-interest requirements, suppression sources, volume caps, and sender ownership. List prohibited personalization such as sensitive attributes or inferred financial distress. Require a human-approved target definition before collection begins. Record the operation against stable identifiers such as prospect_id, company_domain, ad_source_url, ad_observed_at, ad_summary, preserve the raw source reference and capture time, and write any transformation or decision into the system’s change history rather than replacing the prior value. Before the step is marked complete, a human approves the outreach hypothesis and message before activation while n8n revalidates source freshness, contact eligibility, and idempotency; if that check fails, hold stale ads, unverifiable founder matches, prohibited contacts, weak service relevance, unsupported personalization, and any record that fails pre-send revalidation; before completion, the accountable operator must perform and record a QA review against the approved field rules and evidence, and any failed check must be held as an assigned exception. Write down the decision criteria, owner, required inputs, and what is deliberately out of scope so the rest of the workflow does not drift.
An approved ad-active ICP and outreach policy.
Running ads is a timing signal, not proof of need or budget quality. Keep it as one evidence field rather than the entire qualification model.
2-3 hours
2-3 hours
Build the Clay prospect table tables for Companies, Ad Observations, People, Contact Points, Research, Outreach Angles, Channel Decisions, Executions, Replies, Suppressions, and Outcomes. Use company domain, source ad URL or library ID, observation date, ad status, ad theme, founder ID, contact provenance, activity evidence, confidence, jurisdiction, and owner. Preserve the exact source and retrieval date for every personalization fact. Keep inferred fields separate from observed data. Record the operation against stable identifiers such as company_domain, ad_source_url, ad_observed_at, ad_summary, founder_id, preserve the raw source reference and capture time, and write any transformation or decision into the system’s change history rather than replacing the prior value. Before the step is marked complete, a human approves the outreach hypothesis and message before activation while n8n revalidates source freshness, contact eligibility, and idempotency; if that check fails, hold stale ads, unverifiable founder matches, prohibited contacts, weak service relevance, unsupported personalization, and any record that fails pre-send revalidation; before completion, the accountable operator must perform and record a QA review against the approved field rules and evidence, and any failed check must be held as an assigned exception. Ask for a working draft with named sections, assumptions, gaps, and review flags rather than treating the first AI answer as final.
A prospecting system that retains ad, founder, contact, and outreach provenance.
Pro workflow preview
Previewing 2 of 13 steps
Get the remaining 11 steps, copy-paste prompts, pro tips, tool-by-tool setup guidance, and ongoing workflow and prompt releases.
$9/month
The evidence record protects the sender. They can verify the live ad and founder context before approving any message.
Related workflows
Continue with workflows that share a similar GTM motion, category, or tool stack.
A stateful account decision system with signal provenance, deterministic exclusions, ranked eligible actions, approvals, safe execution, outcomes, and policy audits.
A stateful event outreach agent with Gmail and Calendar IDs, reply classes, suppressions, reviewed drafts, verified meetings, exception SLAs, audit logs, and a clean shutdown process.
A governed paid-media change ledger and experiment memory with snapshots, hypotheses, approvals, execution evidence, rollback rules, result classification, and reusable learnings.