Commercial Instant Design

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 Instant Design

A commercial instant design workflow that helped dealers adjust layouts, validate output, and generate proposal-ready artifacts faster.

Skills applied:

Visual Design Interaction Design Prototype Dev Research Information Arch

Dealer-led solar proposals were slowed by fragmented design edits, unclear production impact, and handoffs between layout decisions, savings estimates, BOMs, and proposal artifacts.

I designed a guided instant design workflow where dealers could edit roof layouts, see energy impact, manage change-order risk, generate BOMs, and move toward customer-ready proposals.

The Problem

Dealer design work was trapped between layout, sales, and operations.

Dealers needed to adjust solar layouts quickly during the sales process, but every design decision had downstream consequences.

Changing panel count, roof placement, production estimates, contract assumptions, savings projections, or BOM details could affect the proposal and trigger internal review.

The problem was not simply drawing panels. It was connecting design iteration to customer value, contract status, and fulfillment-ready outputs.

diagram instant 01 — Layout changes created friction across sales, contracts, and outputs.

Without a tighter workflow, dealers risked moving too slowly, overpromising system performance, or sending proposals that required backtracking later.

Solution

Creating a design workspace for fast dealer iteration.

I designed the experience around a central rooftop canvas where dealers could edit layouts visually and understand system impact immediately.

The canvas made the design feel tangible. Dealers could see roof planes, panel placement, current panel count, energy production, energy need, and offset percentage in one place.

sunpower eddie agents 01 — The design canvas let dealers place panels and see energy offset instantly.

This helped reduce the gap between technical layout work and sales conversation. A dealer could adjust the design while still understanding whether the system met the customer’s energy goals.

Making design changes safer

One of the most important design decisions was surfacing contract impact directly inside the workflow.

When a design change affected the current contract, the interface made that risk visible and prompted the dealer to initiate a change order instead of burying that consequence later.

sunpower eddie agents 02 — Change-order warnings made contract impact visible during design edits.

That warning transformed the tool from a drawing interface into a decision-support system. It helped dealers understand when a design edit was no longer just a layout change, but a business workflow change.

diagram instant 02 — Instant Design connected layout edits to energy, contracts, and outputs.

Supporting roof-level editing and real-time feedback

The tool needed to support precise edits without overwhelming the user. Roof selection allowed dealers to isolate one roof plane, adjust panels, and see updated production values.

sunpower eddie agents 03 — Roof selection helped dealers focus edits on one roof plane.

This mattered because solar layouts are spatial and conditional. A design can look simple at the whole-roof level, but every roof plane can carry different capacity, orientation, production, and usability implications.

After adjusting a roof plane, the tool updated panel count, energy production, and energy offset in real time.

sunpower eddie agents 04 — Panel changes updated production and offset calculations in real time.

The immediate feedback loop made iteration feel safe and understandable. Dealers could explore tradeoffs without waiting for separate calculations or external support.

Turning a layout into BOM-ready system data

Once a design became viable, the next challenge was making it operationally useful.

I designed advanced output tools that connected panel selection and layout decisions to the bill of materials. This helped move the experience beyond visual design and into implementation readiness.

sunpower eddie agents 05 — Advanced tools converted the design into BOM-ready output.

This was important because a proposal is only valuable if it can eventually become a real system. The interface had to support both persuasion and execution.

Connecting design decisions to the customer value story

The Savings tab helped translate technical design into a customer-facing explanation of value.

Instead of only showing panels and offsets, the experience showed projected energy savings and system performance in a format that could support a sales conversation.

sunpower eddie agents 06 — Savings views translated design decisions into customer-facing value.

The proposal output extended that value story into a polished artifact. It helped dealers move from design exploration to a professional customer deliverable.

sunpower eddie agents 07 — Proposal output turned the design into a polished sales artifact.

Giving teams usable outputs after the design session

The final outputs screen organized the design into structured system data: BOM, system details, user inputs, and design output summary.

sunpower eddie agents 08 — Outputs organized BOM, system details, and design summary data.

This gave dealers and internal teams a shared reference point. The design was no longer just something visible on the canvas, it became a structured package of information that could support review, proposal, and fulfillment.

Outcome

Commercial Instant Design made dealer-led solar proposals faster and more connected.

The redesigned workflow helped dealers iterate layouts faster, understand energy impact instantly, manage contract risk, and turn design decisions into proposal-ready outputs.

diagram instant 03 — Design decisions flowed into BOM, proposal, savings, and output artifacts.

Estimated impact based on project context:

Faster solar layout iteration
Clearer energy-offset feedback during design
Reduced dependency on separate calculations
Safer handling of contract-impacting changes
Better connection between layout, savings, proposal, and BOM
More confident dealer-led sales conversations

The project showed how a solar design tool could become more than a canvas. By connecting design, savings, proposal, and outputs, it became a complete workflow for moving from roof layout to customer-ready decision support.