I don't manage,
I ship.

The problem. Inbound came from three places (web forms, event lists, Apollo activity) and reps spent their day cleaning contact data instead of calling people. No system turned a raw inbound signal into a rep-ready, enriched contact automatically.

What I built. Inbound automation that turns a raw signal into a rep-ready contact with no human touch:

• A Claude agent resolves company identity from the email domain
• ZoomInfo enrichment attaches contacts and firmographics automatically
• Routing assigns the right rep by territory and quota fill
• Web inbound, 400+ event leads (a $38M+ TAM), and Apollo activity all flow through the same pipe

Underneath it: a CRM data model I designed from scratch across 4 core objects, and 600+ documented changes shipped in 90 days with zero onboarding.

The failure that taught me the most. Before the attribution chain existed, $10.91M in marketing-sourced pipeline sat misattributed in the CRM, invisible to the team that earned it. The early system assumed source data would arrive clean. It never did. The fix was not cleaning records by hand. It was building inheritance: a Contact to Lead to Account to Opp attribution chain across 4 production automations with a standardized 8-value taxonomy, so the truth propagates instead of being re-entered.

Also in this system: a 4-automation bidirectional Apollo integration, 6 stage gates with a Slack bot that DMs reps their exact missing fields, and the attribution chain above.

The problem. A raw construction TAM is not a market. You have to separate real equipment buyers from dealers, media, and design-only firms, find a real commercial moment, and then actually send something a real company's reputation can stand behind.

What I built. A gate-first outbound system where only real buyers make it through:

• A qualified TAM of 631 US heavy-civil contractors; dealers, design-only firms, and media rejected up front
• A Fit Score built on disqualification logic and public award evidence
• A reusable ICP Fit Gate that takes a plain-English ICP as input
• An n8n daily permit watcher with stable dedupe
• The send path: Clay list to n8n send engine to Gmail, and the reply back through a watcher into Clay

The failure that taught me the most. The first real reply almost slipped through. My watcher filtered case-sensitively for "Re:" and Gmail delivered "RE:", so the loop dropped it. I made the filter case-insensitive, republished, and the next poll caught it automatically. A bug found in production, fixed live. That is the difference between a loop that could theoretically work and one that actually closed. The reply came from an equipment leader at a top ENR heavy-civil contractor, who walked through exactly how his team decides rent versus own.

The ethics moment. Every draft had a value line offering an "anonymized 600-contractor study" that did not exist. I cut it before sending and replaced it with something true. "Offer value" is not a line you add to an email; it has to be true before you hit send.