Commercial Ordering System

Portfolio, Ventures & What I Build

Product/systems design that turns AI tech into business results

I'm Gil, an AI Product Design Engineer. I take complex workflows and turn them into AI-native systems, from discovery through shipped product.

My north star is the complete practitioner: the idea that the best AI-native products are shaped by one mind that can hold design, engineering, and AI logic simultaneously, not handed off through layers of interpretation.

When the same person who defines the workflow also builds the prototype and wires the AI, translation loss disappears. Teams move faster and the gap between what we designed and what shipped closes.

What I Bring

Enterprise Systems

Enterprise End-to-End Systems Builder

I've designed complex product ecosystems at enterprise scale — multi-product platforms, multi-role workflows, and long-running transformation initiatives as a solo designer. Systems thinking, not just screen design.

AI Product Engineering

AI-Native Product Design Engineer

I design and prototype AI-native product systems — RAG pipelines, agentic workflows, human-in-the-loop interfaces, structured outputs, and context-aware products. AI product work grounded in real systems, not demos.

Education & Evangelism

Technical Educator & Evangelist

I help people understand, adopt, and build with new technologies — through demos, workshops, tutorials, and product systems thinking. Teaching as adoption; adoption as product design.

A consistent practice across technology cycles

Tech Speaker Microsoft · 5,000+ developers

Co-founder 8th Light · Digital transformation

Startups + Enterprise Engine Yard · ThoughtWorks · Dev tools

Founder Skowak · Design engineering · Teaching

Enterprise Focus SunPower · Digital transformation · Ecosystems

AI Eng Focus Craftal · CareDash · Multi Agent Systems

Now Contextus · Craftal v.2 · AI-native systems

How I Work

I don’t start with AI. I start with how work actually happens.

The method works in cycles. Each one scoped small enough to prove value fast, wide enough to compound across the whole system.

Each cycle makes the next one faster, safer, and more valuable. Real workflows before AI use cases. No baseline, no proof. No proof, no scale.

01 — 03

Understand

Discover
Model
Baseline

Know before you build

04 — 06

Intervene

Design
Adapt & Script
Measure

Build small, prove value

07 — 08

Promote

Promote
Orchestrate

Make it durable and connected

09 — 10

Scale

Govern
Reuse & Expand

Govern and compound

Where most AI projects break down

Most AI failures aren't technical. They're structural: siloed teams, AI built without real workflows, ideas that can't survive contact with production. The method closes those gaps.

Design, engineering, and AI in separate rooms

Work lands in three different hands. Every handoff is a translation, and translation is where ideas lose fidelity.

One practitioner across all three layers

I lead design, write code, and wire the AI as one strategic partner across all three disciplines. No handoffs, no interpretation layers, no gap between what was designed and what shipped.

AI built without a workflow to plug into

Teams rush to launch LLM features with minimal ROI. Without mapping real workflows or solving real problems, the result is unused chatbots and shallow automation.

Bridge between LLMs and real work

I map how work actually happens first, then wire the AI stack into those real decisions. The result is automation that runs, not a chatbot no one uses.

Technical Toolkit

The full stack, from workflow model to deployed AI system.

My stack spans the full system: AI engineering (OpenAI & Anthropic APIs, LangChain, LangGraph, DSPy, RAG pipelines, vector stores, structured outputs, agent orchestration), frontend and prototyping (React, Angular, Vue, TypeScript, API-connected interfaces), backend and tooling (Python, FastAPI, Rails, PostgreSQL/pgvector, Docker), and product and design (systems modeling, workflow mapping, information architecture, interaction design, design engineering).

As a product generalist, I choose the right tool for each layer (design, front end, data, or model) so ideas travel from workflow model to shipped system without unnecessary handoffs.

Getting personal

Things I do when I'm not building

Still-life sketching, coastal hiking, PC teardowns, and slow travel through cities with good architecture.

I draw to stay sharp. I travel to stay curious. I take things apart to stay honest about how they work.

Back

Commercial Ordering System

A redesigned commercial ordering workflow that turned complex solar BOMs into faster, reusable dealer orders.

Commercial dealers were stuck rebuilding complex solar orders manually, creating delays, errors, and frustration across the ordering process.

I redesigned the experience around reusable BOMs, guided product selection, checkout clarity, and order tracking, helping dealers move from painful manual work to a faster commercial ordering flow.

The Problem

A critical workflow buried inside a painful ordering experience.

Commercial solar ordering was one of the most important workflows in SunPower’s dealer ecosystem. Dealers needed to assemble modules, inverters, accessories, monitoring equipment, and system packages into complete commercial orders.

The old experience made that work harder than it needed to be. Dealers had to navigate dense product lists, manually rebuild repeated configurations, and rely on error-prone steps to submit complex commercial orders.

diagram ordering 01 — The old ordering flow created repeated correction loops.

The business problem was not just usability. Ordering errors affected fulfillment, back-office correction cycles, dealer confidence, and project momentum.

SunPower needed a faster ordering experience that helped dealers place accurate commercial orders without depending on internal teams to clean up avoidable mistakes.

Solution

Turning ordering into a guided commercial workflow.

I redesigned the ordering experience around the way commercial dealers actually thought about solar systems: categories, system components, reusable configurations, and operational status.

sunpower commercial ordering 01 — Commercial ordering began with catalog categories and Helix system promotion.

Instead of treating the interface like a static product catalog, the new experience behaved more like a guided ordering workspace.

Dealers could browse product categories, add quantities, review cart contents, and move toward checkout with a clearer sense of what they were building.

sunpower commercial ordering 02 — Product tables helped dealers compare specs and add components quickly.

The interface organized complex solar components into recognizable commercial categories: modules, inverters, accessories, systems, specials, shopping cart, and timeline.

That structure reduced cognitive load. Dealers no longer had to hold the entire order in their heads while jumping through disconnected screens.

sunpower commercial ordering 04 — Accessory ordering supported technical components beyond panels and inverters.

Designing for reuse, accuracy, and operational confidence

The strongest improvement was the shift from one-off order entry to reusable commercial ordering logic.

A dealer could associate an order with an existing sales opportunity, pick an approved system design, verify addresses, and move through a structured order submission flow.

sunpower commercial ordering 05 — The order flow connected CRM context, design selection, and fulfillment details.

This mattered because commercial solar orders are not simple purchases. They depend on project context, system design, shipping details, billing information, and downstream fulfillment coordination.

The new flow made those dependencies visible. It helped dealers understand what needed to happen before checkout, what information was missing, and how the order connected to a real commercial project.

diagram ordering 02 — The redesign turned ordering into a guided project workflow.

Making order status visible after submission

The system also needed to support what happened after checkout.

Dealers and internal teams needed visibility into submitted orders, delivery confirmation, site readiness, pending steps, and order history. The timeline view transformed ordering from a single transaction into an operational tracking experience.

sunpower commercial ordering 06 — Timeline tracking gave dealers visibility after order submission.

The booked orders view gave teams a searchable, filterable way to manage order status, dates, holds, CSV export, and timeline access.

sunpower commercial ordering 07 — Booked orders supported filtering, export, and operational follow-through.

Outcome

A dealer workflow that felt dramatically more usable

The redesigned Commercial Ordering System gave dealers a clearer, faster way to build and submit commercial solar orders. It reduced the burden of assembling complex BOMs manually and made the ordering process feel more reliable.

diagram ordering 03 — Post-order visibility reduced uncertainty across teams.

The work also gave SunPower a stronger commercial platform pattern: product categories, cart logic, opportunity context, design selection, checkout, and timeline tracking working together as one connected experience.

Estimated impact based on project context: