Helix Calculator

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

A CAD-like commercial solar design tool that helped dealers create accurate rooftop layouts in minutes instead of days.

Skills applied:

Visual Design Interaction Design Prototype Dev Information Arch

Commercial solar design depended on engineering support, static drawings, spreadsheets, and slow back-and-forth cycles that delayed proposals and limited dealer autonomy.

I designed a CAD-like web tool that turned roof layouts, wind zones, anchors, ballast rules, panel logic, outputs, and BOM generation into one guided commercial design workflow.

The Problem

Commercial solar design was too slow for modern dealer-led sales.

Commercial dealers needed to design large rooftop solar arrays quickly, but the workflow depended on engineering expertise, manual CAD work, spreadsheets, and repeated clarification cycles.

Every commercial roof introduced technical complexity: geometry, obstructions, wind zones, anchors, ballast, panel types, production assumptions, and code-driven constraints.

Dealers needed speed and clarity. Engineers needed accuracy and rule enforcement. The existing workflow forced both groups into slow back-and-forth communication.

diagram helix 01 — The old workflow pushed every layout through engineering bottlenecks.

The business problem was bigger than drawing panels on a roof. Slow design cycles delayed proposals, increased engineering escalations, and made commercial solar harder to sell at scale.

Solution

Designing a CAD-like workspace for commercial solar.

I designed Helix as a commercial solar design workspace, not a generic calculator.

The goal was to give dealers enough power to create credible commercial layouts without exposing them to unnecessary engineering complexity. The interface needed to feel visual, direct, and fast while still respecting the rules that made the design valid.

sunpower helix 01 — Helix started from a dashboard built around active commercial design work.

The dashboard gave dealers a clear starting point for active projects, recent activity, design imports, and calculator access. It framed Helix as a full design environment rather than a one-off utility.

sunpower helix 02 — Project cards made commercial design progress visible across sites.

Project cards helped dealers and internal teams understand where each design stood. Status, progress, capacity, panel count, system type, and client context were visible before entering the canvas.

Turning roof data into a visual design canvas

The core design challenge was translation. I had to convert engineering logic into interface behavior: zones, panels, anchors, ballast, warnings, summaries, and output states.

The canvas became the center of the experience. Dealers could load system data, inspect the roof layout, switch between analysis modes, and progressively understand what the design required.

sunpower helix 04 — The canvas supported CAD-style workflows and system data imports.

This import step mattered because Helix needed to work with real project data, not abstract mock layouts. DXF, CSV, and JSON import options allowed the design workflow to start from structured site information.

diagram helix 02 — Helix turned engineering logic into layered visual guidance.

Making invisible engineering constraints visible

Helix exposed technical constraints as visual layers. Instead of forcing dealers to interpret spreadsheets or wait for engineering interpretation, the product showed rules directly on the roof.

Wind analysis, anchor requirements, panel types, ballast conditions, and permit-related logic became selectable modes in the same workspace.

sunpower helix 06 — Wind zones translated engineering constraints into visible roof regions.

The wind layer made environmental constraints visible across the rooftop. Dealers could immediately see how roof position affected design decisions instead of waiting for engineering review.

sunpower helix 07 — Anchor analysis exposed structural rules directly inside the design canvas.

The anchor layer helped translate structural requirements into placement logic. This reduced guesswork and made engineering assumptions easier to understand during layout creation.

sunpower helix 08 — Panel types helped dealers understand layout rules without engineering handoffs.

Panel classifications gave dealers a visual way to understand corner, edge, and interior conditions. The interface taught the rules through the layout itself.

Connecting visual layout decisions to engineering calculations

The tool was not just a drawing surface. It needed to produce useful technical outputs.

I designed calculator panels and output summaries that connected site inputs to feasibility, safety, material quantities, and commercial ordering requirements.

sunpower helix 10 — Ballast calculations connected site conditions to system feasibility.

The calculator panel made structural inputs part of the workflow: building dimensions, parapet height, wind speed, exposure category, block type, and ballast constraints. Dealers could calculate without leaving the design context.

sunpower helix 13 — Outputs converted the visual layout into engineering and BOM data.

The outputs panel transformed design activity into actionable information: total panels, ballast blocks, total weight, anchors, subarray counts, wind-zone breakdowns, and BOM preview.

Packaging the design into a usable report

The final step was making the output portable. Dealers and internal teams needed a summary they could review, export, print, or share.

sunpower helix 15 — Summary reports packaged layout, ballast, anchor, and subarray results.

The summary report turned a complex design session into a clean project artifact. It gave teams a shared reference for panel count, ballast, weight, PSF, anchors, zones, and warnings.

Outcome

Helix reduced dependency on engineering and accelerated commercial proposals.

Helix helped convert commercial rooftop design from a specialist-driven process into a dealer-accessible workflow. Dealers could create and revise large commercial layouts faster, while engineers received cleaner inputs and fewer low-value escalations.

diagram helix 03 — Layout decisions became validated outputs dealers could act on.

Estimated impact based on project context:

Commercial layouts reduced from hours or days to 10–25 minutes
Revisions reduced to under 5 minutes
Engineering escalations reduced by 40–60 percent
Time-to-quote reduced by 25–40 percent
Dealer autonomy increased
Proposal inputs became more consistent

The project proved that CAD-like complexity could become usable web software when engineering rules were translated into thoughtful interaction design. It remains one of my clearest examples of design engineering applied to a technical, operational domain.