Consumer-Direct - Life Insurance

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

Consumer-Direct - Life Insurance

A direct-to-consumer life insurance experience that helped customers quote, qualify, sign, and submit online.

Skills applied:

Visual Design Interaction Design Prototype Dev Research Information Arch

Buying life insurance online is usually intimidating. Customers face personal questions, health disclosures, state restrictions, pricing decisions, authorization documents, and uncertainty about what happens after submission.

I helped design ConsumerDirect as a self-guided life insurance experience that translated a complex regulated workflow into a clear, approachable consumer journey. The product guided users from quote discovery to eligibility, plan selection, e-signature, and final submission without requiring an agent at every step.

The Problem

Life insurance felt too complex for self-service.

The business wanted a consumer-facing path that could support instant quoting and online enrollment. But the underlying workflow was not simple. Life insurance requires identity details, age and gender inputs, height and weight, state availability, eligibility questions, medical history, plan selection, authorization documents, and underwriting review.

The challenge was to make the process feel fast and approachable without hiding the seriousness of the decision. The experience needed to reduce fear, avoid form fatigue, and keep customers moving through a regulated application flow with confidence.

diagram consumerdirect 01 — Online life insurance created anxiety, form fatigue, and uncertainty for customers.

Solution

A guided application experience that felt more like onboarding than paperwork.

I designed ConsumerDirect around a step-by-step journey. Instead of showing customers a long insurance form, the interface broke the experience into focused moments with clear progress, plain-language explanations, and visual reinforcement.

fidelitylife cd 01 — The landing page framed the product around speed, simplicity, and instant approval.

The homepage positioned the product as accessible life insurance without agents, medical exams, or paperwork. The interface used clear pricing, trust signals, and a direct call to action to reduce hesitation before the application began.

fidelitylife cd 03 — The first step captured basic identity details with a friendly onboarding tone.

The application flow started with the simplest possible information: name and email. This gave the experience a low-friction entry point before moving into more sensitive insurance questions.

fidelitylife cd 04 — Date of birth and gender were translated into an easy guided step.

Age and gender affect rate calculations, so I treated those inputs as a dedicated step. The interface made the logic visible without making the experience feel like a traditional insurance form.

fidelitylife cd 06 — Height and weight inputs used visual controls to make health data feel less clinical.

For health-profile data, I used more visual interaction patterns instead of plain text fields. This helped make personal health information feel easier to answer while still collecting structured data.

diagram consumerdirect 02 — ConsumerDirect turned regulated insurance intake into a guided customer journey.

State selection made product availability and regulation feel understandable.

fidelitylife cd 08 — Eligibility provided dynamic constraints to both the interaction design scope as well as the business logic.

Because insurance availability varies by state, I designed the location step as a visual state selection experience. This made a regulatory requirement feel like a normal part of the quote journey.

fidelitylife cd 13 — Eligibility questions used simple yes/no choices to reduce decision friction.

The eligibility section asked required underwriting questions in a clean, structured format. Customers could answer quickly without feeling overwhelmed by a dense application form.

fidelitylife cd 16 — The quote screen let customers compare coverage options and choose a plan.

The quote step was the emotional payoff. Customers could adjust coverage, compare term options, understand monthly cost, and choose a plan before signing authorization documents.

Outcome

A complete self-service path from quote to application submission.

ConsumerDirect gave customers a clearer way to apply for life insurance online. The experience supported discovery, qualification, quote comparison, e-signature, and submission inside one coherent flow.

fidelitylife cd 24 — The authorization checklist showed signed documents and remaining actions clearly.

The e-signature experience was especially important. The interface separated required documents into individual cards, tracked progress, and made it clear when the customer was ready to submit.

diagram consumerdirect 03 — A clear funnel helped customers move from quote discovery to submitted application.

The final state closed the loop by confirming coverage progress, showing the selected plan, and explaining next steps such as email confirmation, application review, and coverage activation.