AI Product · Automation · Lead-to-Cash

I build AI systems that run the whole funnel.

Solo-built and shipped Flowmation — a production AI automation system for real-estate lead-to-cash. From problem to pipeline to a data-grounded optimization program: designed, engineered, and run by one person.

The system, end to end
01
Source
Targeted leads, pulled by a repeatable method
02
Validate
Every lead deliverability-checked before send
03
Engage
Personalized outreach in under a minute
04
Follow up
Automated until they reply — then it stops
05
Measure
Controlled A/B tests read the results
<60s
automated lead
response, verified live
100%
deliverability-validated
sourcing (latest cohort)
0→1
built from scratch,
solo, end to end
A/B
controlled experiments
with statistical design
Flagship · 2026 · flowmationai.io

Flowmation — an AI system for real-estate lead-to-cash

Agents lose deals to whoever replies first. A lead that waits hours is usually gone — but an agent can't leave a showing to answer every inquiry. Flowmation closes that gap: it responds to every inbound lead in under a minute, follows up until they answer, and runs the whole funnel — sourcing, engagement, and measurement — without manual work.

What I owned

Everything. Problem discovery and positioning, the system architecture, the code, the outreach copy, the experiment design, and the analysis. I defined what success looked like, built the thing that pursued it, and instrumented it so the results could be read honestly.

How I optimize it

A structured experimentation program — hypothesis-driven, statistically framed (sample sizes, base rates, expected outcomes), one variable at a time — so the funnel improves on evidence rather than instinct.

Architecture

Control planeGoogle Apps Script + Sheets
OrchestrationMake.com · webhook-driven
GenerationAnthropic Claude API
DeliveryGmail
ValidationZeroBounce
SafetyKill switch · audit trail · logging
Selected builds

Systems inside the system

Each of these is a working component I designed and shipped — not a mockup. Together they form the pipeline above.

01Verified live

Instant Lead Responder

An inbound lead triggers a personalized reply that's written and delivered in under 60 seconds — webhook → Claude API → Gmail. Built and verified end to end, so no inquiry ever sits cold.

LLM integrationevent-driven<60s
02In production

Cohort Experimentation Framework

Routes leads to isolated variants by cohort while holding the message body as a controlled constant — so a subject-line test measures the subject line and nothing else. Designed for clean causal reads.

experiment designrouting logiccausal isolation
03Repeatable

Sourcing & Validation Pipeline

A documented, repeatable method that sources targeted leads and validates 100% of them for deliverability before a single send — with query variations rated by yield so the process compounds.

data pipelineZeroBouncemethodology
04Automated

Follow-Up Engine

Time-triggered follow-ups that keep going until a lead replies — then stop the instant they do. Ships with a kill switch, failure logging, and an audit trail that reconciles every send. Fails loud, not silent.

reliabilitysafety-by-designautomation
05Multi-channel

Content & Messaging System

One controlled content pipeline across web and email — generation, brand consistency, and versioned publishing — so what ships is on-brand and on-message everywhere, every time.

content opspublishingbrand consistency
06Judgment call

Model-Use Discipline

Pulled the LLM out of the send path when a fixed template served the experiment better and cheaper. Knowing when not to use the model is as much the job as knowing when to.

AI product judgmentcost/qualitytradeoffs
How I work

Operating principles

The habits that show up in everything above — and the reason the work holds up when you look closely.

P.01

Data over instinct

Every call framed with the math — sample sizes, base rates, expected outcomes. Forecasts before results, so we optimize on evidence, not vibes.

P.02

Isolate one variable

Clean experiments only. When a subject line is under test, the body is a controlled constant — so a result actually means something and can be trusted.

P.03

Verify, don't assume

Nothing ships on trust. Live test-sends, config checked against source, audit trails reconciled. "It should work" isn't the same as "I watched it work."

P.04

Safe by construction

Kill switches, pristine rollback baselines, failure logging, syntax-checked deploys. Systems designed so the expensive mistakes are hard to make.

What I bring

Competencies

AI Product Management
Problem discovery → solution design → hypothesis-driven iteration. Defining success metrics and instrumenting the product so they can actually be measured.
Value Realization
Framing the outcome and the ROI logic behind a build — designing for measurable business impact, not features for their own sake.
Lead-to-Cash Systems
End-to-end funnel ownership: source → engage → follow up → convert → measure, wired together as one instrumented operation.
Content & Publishing Ops
A controlled multi-channel content pipeline — generation, brand consistency, and versioned publishing across web and email.
LLM / AI Integration
Claude API orchestration, prompt design, and the judgment to know when a model is the right tool — and when it isn't.
Experimentation & Analytics
A/B design with statistical rigor, controlled variables, and honest reads of what the data does and doesn't say.
Automation Engineering
Make.com, Google Apps Script, webhooks, and API integrations — the plumbing that turns a plan into a running system.
Let's talk

Building something with AI?

I'd like to help you ship it — and measure whether it worked.