Learner Launch

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 student-facing app that turned learning plans into clear, motivating daily actions.

Skills applied:

Visual Design Interaction Design Research Information Arch

Flexible learning only works if students understand what to do next. Learners needed a calm, age-appropriate interface that translated parent plans into clear daily focus, without exposing the full complexity of scheduling and resource management.

I designed the Learner Launch app as the student-facing side of the Colearn ecosystem. It helped learners see active blocks, complete tasks, request help, review finished work, and access resources from one simple workspace.

The Problem

Parent-led learning creates a second challenge after planning: execution.

Even if parents organize the week well, learners still need to understand what matters right now.

Without a dedicated learner experience, students can become dependent on constant parent direction. They may not know which block is active, which tasks are complete, what needs review, or where to find the right resource.

diagram learner 01 — Learners needed daily focus without depending on constant parent direction.

The interface had to support younger students without making the experience feel childish or overwhelming. It needed to be clear enough for independent work, but structured enough for parents to trust.

The product also needed to connect back to the Parents App. Learners should see their own simplified workspace, while parents maintained planning, safety, and progress oversight elsewhere.

Solution

A Learner Launch tool around a simple question: what does the learner need to do today?

The main workspace translated the parent’s plan into three clear zones: available blocks, current focus, and work for review. This helped learners understand where to start, what was active, and what was waiting for feedback.

colearn learner 01 — Learner workspace showing blocks, focus work, help needs, and review tasks.

The left column gave learners a backlog of available blocks. The goal was to make learning feel selectable and concrete, not buried inside a complex calendar.

The center area represented immediate focus. Instead of showing an entire week of detail, the interface surfaced the active block with its task checklist, subject tag, and completion status.

This gave the learner a practical sense of progress. They could complete steps one by one, see what remained, and understand when a block was ready to move forward.

diagram learner 02 — Parent plans became simple learner actions inside a focused workspace.

The Need Help area was important because independent learning still requires support. Learners needed a lightweight way to signal confusion without breaking the rhythm of the experience.

This turned help into part of the workflow rather than a separate conversation. Parents could see where support was needed, while learners had a clear place to express blockers.

The For Review panel created a second important state: work that was finished but not fully closed. This helped learners understand that completion, reflection, and feedback were part of the learning loop.

The Resources menu connected the learner experience to external learning materials. Instead of making learners search across random websites, resources were surfaced in context from the learning environment.

colearn learner 03 — Resource menu connecting learners to approved learning tools and websites.

This design kept the learner experience narrow and purposeful. The student did not need to manage billing, privacy, scheduling rules, or family setup. They only needed the parts of the ecosystem that supported learning action.

The visual direction was intentionally calm and friendly. The rocket theme, soft cards, rounded panels, and simple subject colors helped the product feel approachable without losing structure.

Outcome

Learner Launch completed the loop between parent planning and learner execution.

Parents could create structured learning plans, and students could act on those plans through a simplified daily workspace.

diagram learner 03 — The final system connected planning, focus, help, review, and progress.

The product gave learners more autonomy while preserving parent visibility. Students could see what to work on, complete tasks, request help, and move work into review without needing the parent to constantly interpret the plan.

The larger outcome was ecosystem coherence. The Parents App handled planning and oversight. Learner Launch handled daily focus and execution. Together, they formed a clearer operating model for flexible education.