Portfolio

Work that ships

Reporting dashboards, AI workflow automation, software setup, and web design. Real work, built for small businesses

AI Workflow Automation + Reporting & Dashboards + Software Setup

Insurance Holding Company: AI Compliance Automation

This client operates a portfolio of insurance brands that serve diverse communities across the U.S., and one of those brands generates a constant stream of new policy paperwork that has to be checked for completeness before it turns into a liability. We built a pipeline that pulls new policy documents in every morning, reconciles each one against the underlying transaction records, and runs a scalable, multi-rule AI compliance audit on every packet, verifying thousands of documents in minutes instead of hours, all before 9:30 AM with no one touching it. A second AI model checks every score independently, so anything the two disagree on gets flagged for a person instead of quietly slipping through. It runs on a single cloud server sized correctly for the job, one that spins up, works through the day's batch, and shuts itself down, and the whole system was built and put into production in 30 days. On day one, before the system had learned a single pattern, it already surfaced over $44,000 in premium tied to policies with zero compliance documentation on file.

Every rule that code can answer runs in code first. AI only gets called when the answer is genuinely ambiguous, cutting audit cost by 50 to 70 percent and bringing a full compliance review down to roughly six to fifteen cents per policy packet, whether it's a dozen documents or a few thousand.

Client identity confidential. Part of the same insurance holding company engagement featured further down this page

AI Automation Claude API Two-Model Verification Snowflake AWS EC2 Google Drive Cron Automation Compliance Audit Cost Optimization Reporting & Analytics High-Volume Processing
Daily Compliance Pipeline
Policy Documents Received
Reconciled to Transaction Records
Scalable Multi-Rule AI Audit
Two-Model Verification  ·  Cost-Optimized Routing
Snowflake
Structured Results
Reporting Layer
Office & Carrier Analytics
1000s
Docs Verified in Minutes
50-70%
Fewer AI Calls
$0.06-$0.15
Cost per Packet
0
Manual Touchpoints
AI + Google Workspace Automation

Intelligent Email Triage System

A local small business was drowning in emails and falling behind on client onboarding. We built a Google Apps Script system that runs daily: an AI agent scans the inbox, prioritizes urgency, drafts replies, and logs everything to Google Sheets. When a new client contract is detected, a full onboarding workflow fires automatically.

Two automation tracks running in parallel: daily AI email management and a new-client trigger that sets up folders, templates, and shared files without human input
Google Apps Script Gmail API Google Sheets AI Drafts Automated Onboarding Agentic AI
Agentic AI for Emails
Inbox Scan Prioritize AI Draft Replies Log to Sheets

AI Automations: New Client Trigger
Contract Detected Create Folder Apply Templates Share Files Notify Client
SaaS Setup + AI Automation

HoneyBook Client Operations System

Full HoneyBook setup for a service business: client portal, branded proposal and contract templates, automated follow-up sequences, AI-assisted note-taking during calls, and scheduler integration. New clients get onboarded automatically.

A new inquiry goes from first contact to signed contract to active client portal, automatically, with no manual steps in between.
HoneyBook AI Notes Automation Client Portal Scheduling
01Lead Inquiry
02Auto Questionnaire Sent
03AI Note-Taking Active
04Proposal + Contract Sent
05Client Portal Activated
06Customized Client Portal
07Automated Follow-ups Begin
Data Analytics + Interactive Dashboard

Project Reimbursement Dashboard

Built for a local agency administering residential energy grants across two state programs. Tracks project status, funding utilization, and reimbursement pipelines, with filterable views, a live county-level choropleth map, and real-time breakdowns by status and income level.

Hover any county to see project count, total cost, status breakdown, and income distribution in real time
Client data protected: charts use anonymized data. No real identities or figures displayed
JavaScript SVG Choropleth Map D3-style Charts Filter Logic Data Analytics
Web Design + AI Automation + Software Setup

Red & Gold Events

Georgia's leading South Asian wedding planning company needed more than a website. They needed a full business operation built from scratch. We designed and launched the site, then built every system behind it: HoneyBook configured end-to-end for bookings, contracts, and client communications; Google Drive and Docs organized for client-facing document management; 1099 payroll set up for their team; and AI automations that calculate hourly pay automatically, eliminating manual tracking entirely.

Every piece of their business now runs on systems they don't have to think about. That was the goal.
Visit Live Site
Web Design HoneyBook Google Drive & Docs 1099 Payroll AI Automation Hourly Pay Calculation Client Onboarding Contract Management
Web Design + Live Automation

Live Automated Display System

A live session display built for a Johns Creek, GA nonprofit. It replaces manual bulletin boards with a self-updating schedule that counts down to the next event automatically. No staff input, no daily maintenance, no one responsible for keeping it current. Also configured Wave Apps to automate payroll processing and W-2 generation, eliminating manual year-end prep for the organization's staff.

The organization needed something that just worked. It runs itself.

Client identity masked. Standard practice for nonprofit and community organization engagements

JavaScript Live Data Automated Scheduling Real-time Counter Display System Wave Apps Payroll Automation W-2 Processing
Sessions Lecture Start Lab Start
Time to Next Lab: -- hours -- mins
Live
Data Engineering + Enterprise BI

Insurance Holding Company: Data & Reporting Architecture

A financial services holding company that runs a portfolio of insurance brands serving diverse communities across the U.S., pairing local market expertise with national operational scale. The organization provides the infrastructure, technology, and strategic leadership required to grow insurance service businesses at scale: acquiring and investing in agencies, delivering shared services and compliance, and enabling scalable growth without compromising brand identity.

Served as Data and Reporting Architect to the CIO. Built Matillion ELT pipelines from the ground up, coordinated secure vendor data transfers, led report design initiatives, and delivered analytics on customer retention and financial performance.

Client identity confidential. Standard practice for enterprise and financial services engagements

Matillion ETL AWS S3 AWS EC2 Snowflake RDS Migration Data Engineering DBA Legacy Conversion Tableau Power BI AI Analytics
Data Pipeline Architecture
Source Layer
Legacy Systems
RDS Databases
Vendor Feeds
Matillion ETL
ELT Pipelines  ·  Secure Transfers  ·  Transformations
AWS S3
Data Lake
Snowflake
Data Warehouse
Analytics & BI
Tableau
Power BI
AI Analytics
AI Workflow Automation + Software Setup

Automated Contract-to-Onboarding System

Every time this client's contract gets signed, an email arrives, and everything downstream happens without anyone touching it. A folder gets created to file the correspondence, a matching folder gets created in the shared drive, and a full set of client documents gets copied from a template, customized, renamed, and sent out. The system encodes the essential facts, the client's name and the engagement date, directly into a structured ID, so the automation can pull them back out and use them everywhere they're needed: a bookkeeping entry for the contract amount and the next payment due, a scheduling entry so a manager can assign the right team, and a hold placed on the calendar so nothing else can ever get booked over it. AI only gets involved when the automation hits something it cannot confidently parse on its own, a name or a pattern that does not fit the rule, and even then it asks one narrow question instead of guessing. Once an engagement wraps, the same system closes out the bookkeeping and scheduling entries on its own, so the records stay current without anyone going back to clean them up.

AI is not the backbone here, it is the fallback. Every step that logic and code can handle runs on logic and code. Claude only gets called when the automation genuinely cannot tell what it is looking at, which keeps this fast, cheap, and dependable enough to run unattended every single day.

Client identity confidential. Standard practice for active client engagements

AI Automation Claude API Workflow Automation Calendar Automation Template Generation Bookkeeping Integration Scheduling Automation Cost-Conscious AI
01Contract Signed
02Email + Drive Folders Created
03Client ID Parsed for Name + Date
04Templates Filled + Sent
05Bookkeeping Entry Logged
06Calendar Hold Placed
07Team Assigned via Scheduler
08Closed Out Automatically
Ready to run your business on facts
Let's build the reporting, automation, or software your business actually needs
Get in Touch