01 Build 02 Work 03 About
Product Manager & Builder

I build the systems that make chaos operational.

Knowledge bases, CRM architecture, automation pipelines, AI workflows - connected into one coherent operating system. Clean integrations, real operational improvements.

Get in touch
10+
Years shipping product
20+
Projects with $1M+ impact
1000+
Small and medium projects delivered
500+
Avg hours saved monthly last year
01

Information architecture that your team actually uses

SOPs, client playbooks, decision logs, meeting-to-knowledge pipelines. Notion, Confluence, or custom. Governed so it stays accurate and searchable - not another graveyard of docs nobody reads.

NotionConfluencemonday.comClickUpAsanaHubSpotDjangoPostgresSOPsKnowledge Base
SOP Coverage
02

PM platforms, CRM, integrations - wired end to end

Slack workflows, shared inbox integration, Google Sheets sync. Everything connected so status changes propagate and nothing falls through the cracks.

HubSpotPipedriveJiramonday.comSlackGoogle SuitePostgresDjangoZapiern8nRAGAPI Integrations
System Health
94%
UPTIME
12
ACTIVE
0
BLOCKED
03

The layer that makes everything compound

n8n automation pipelines, AI search and Q&A systems, context architecture that makes AI outputs reliable. Browser automation for repetitive flows. Not magic - structure.

n8nClaude AIAutomationContext Design
Monthly Hours Saved
Selected Work
Case Studies
07 projects
01

Full Operational System - From Zero

Lux D+M | 2024
+

The Problem

A growing FF&E manufacturer with no operational systems. Everything lived in email, spreadsheets, and people's heads. Team across 4 countries.

What I Built

  • CRM architecture (HubSpot) with custom data models and pipeline automation
  • Project management system (Jira) with cross-team workflows
  • Structured knowledge base: SOPs, client playbooks, decision logs
  • Slack integration layer for real-time ops capture
  • n8n automation pipelines connecting all systems
  • AI-assisted estimation engine (FF&E IQ) - reports in minutes, not weeks
30%
Automation increase monthly
6
Team across 4 countries
Min
vs Weeks estimation
HubSpotJiran8nAISlack
02

CRM Platform & Integration Architecture

Ergeon | 70+ eng
+

The Problem

A fast-scaling construction tech company with a CRM held together by workarounds. Manual quoting eating 45+ minutes per lead.

What I Built

  • Owned the CRM platform (Pipedrive + custom Django)
  • Integration portfolio via Zapier and direct APIs
  • Automated quoting engine with dozens of composing variables
  • Automated escalation system with classification and routing
  • Jira-based task management for company-wide adoption
8x
Quoting speed
25%
Escalation reduction
40%
Lead-to-quote
90%
Jira adoption
DjangoPipedriveZapierSQL
03

AI Context & Knowledge Systems

Multiple
+

The Principle

AI outputs are only as good as your information architecture. I design the context layer - constrained inputs, clean metadata - that makes AI reliable.

What I Built

  • AI Designer: natural language to production templates (React Email, Storybook)
  • AI-first Django workflow: descriptions to code with validation
  • Context architecture for AI estimation engine
  • Meeting transcripts to structured KB entries
  • Claude-based search over operational documents
30%
More automated hours
75%
Faster retrieval
Claude AIn8nReact EmailDjango
04

Satellite-Based Quoting System

Ergeon | 200+ users
+

The Problem

Quoting took 2.5 days. Reps manually measuring properties, calculating materials. Two largest teams bottlenecked.

What I Built

  • Satellite-based property measurement in the quoting flow
  • Draft Editor for real-time quote building and preview
  • Pricing engine with dozens of composing variables
  • Mentored 2 junior PMs through the project
2.5d→20m
Quote time
40%
Lead-to-quote
15%
Lead-to-win
DjangoSatellite APIPython
05

Automated Escalation System

Ergeon | Scale
+

The Problem

Escalations eating ~50% of possible profit. No classification, no routing, no pattern visibility.

What I Built

  • Classification system (type, severity, root cause)
  • Automated routing based on classification
  • Resolution tracking with SLA timers
  • Pattern analysis dashboard
  • Feedback loop into SOPs
25%
Escalation cut
6→4wk
Turnaround
$M+
Saved profit
DjangoJiraAnalytics
06

Company-Wide Task Management

Ergeon | All depts
+

The Problem

Every department on different tools, different definitions of "done." No source of truth.

What I Built

  • Jira spanning Sales, Construction, HR, Admin Ops
  • 100+ task types mapped to department workflows
  • 5 integrations: Calendar, Email, Slack, Pipedrive, Django
  • Cross-department handoff automation
90%
Adoption
100+
Task types
5
Integrations
20%
Fewer change orders
JiraSlackPipedrive
07

Remote Design Operations at Scale

Microsoft | 1000+
+

The Context

Fully remote design team of ~15 across time zones - one of the earliest remote roles at Microsoft.

What I Delivered

  • support.microsoft.com design delivery
  • docs.microsoft.com technical documentation
  • Microsoft Teams early rollout contributions
  • Windows icon redesign
1000+
Projects
~15
Team size
4
Product lines
JiraFigmaAgile
Stack
DjangoPostgresBigQueryPythonSQLDockerGitn8nZapierMakeRetoolMetabaseClaude AICursorHubSpotPipedriveJiramonday.comNotionConfluenceSlack APIsGoogle SheetsShopifyFigmaVercelCloudflare
About

Architecture-trained. Tech-wired. I spent nearly a decade working under a co-founder of oDesk/Upwork across three companies. The most important thing he taught me: data, data, and more data points for everything. No gut feelings. Measure it, prove it, then decide.

When I see a broken process, a system held together by workarounds and good intentions, I can't leave it alone. I will map it, instrument it, find where the data says it's failing, and rebuild it.

I sit between engineering and business. When things are chaotic, I'm the person who brings structure - not by adding meetings, but by building systems that make the chaos legible.

Your tools should compound,
not just coexist.

Let's build your operating system.

Get in touch →

I prefer working globally via Upwork - where both client and freelancer are protected.