Colearn Parent App

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 parent planning app that turned scattered learning activities into structured weekly progress.

Skills applied:

Visual Design Interaction Design Research Information Arch

Homeschooling and enrichment planning can quickly become fragmented. Parents need to coordinate multiple learners, subjects, resources, schedules, progress updates, and safety settings without turning education into admin work.

I designed a parent-facing product that helped families plan learning blocks, monitor progress, discover resources, and manage each child’s experience from one calm, structured dashboard.

The Problem

Parents managed flexible learning across many disconnected educational tools.

Using flexible learning programs often had to manage education across disconnected tools: calendars, notes, websites, enrichment providers, progress trackers, and communication channels.

The challenge was not only scheduling. Parents needed to understand what each learner was doing, what needed attention, what resources were available, and whether the overall learning rhythm felt balanced.

diagram parent 01 — Parents needed one place to coordinate learning, progress, and support.

The product also had to support multiple children with different ages, subjects, interests, and learning patterns. A parent might be guiding one child through math, another through language practice, and another through project-based learning.

That meant the product could not behave like a rigid school administration tool. It needed to support planning, flexibility, visibility, and confidence at the same time.

Solution

A Parents App around a clear family command-center model.

The dashboard gave parents a quick read on what had happened recently, who was actively working, and how the family was progressing across the school year.

colearn parents 01 — Dashboard view showing activity, focus, and school-year progress.

This overview was important because parents did not need another place to manually inspect everything. They needed a calm summary that helped them notice progress, spot friction, and decide where to focus next.

From there, the experience moved into planning. The weekly planner helped parents arrange learning blocks across the current week and upcoming week, giving structure without forcing a traditional school schedule.

colearn parents 02 — Weekly planner organizing learning blocks across current and upcoming weeks.

The planning model was based on blocks rather than isolated assignments. That made the system flexible enough for homeschooling, enrichment, tutoring, project-based learning, and recurring practice.

diagram parent 02 — Learning blocks turned loose activities into reusable education units.

Each block could hold the details parents actually needed: subject, duration, resource, instructions, tasks, and recurrence. This helped convert loose ideas like “practice Spanish” or “work on history” into actionable learning units.

colearn parents 04 — Block creation workflow for subjects, resources, instructions, tasks, and recurrence.

Once blocks existed, the daily planner translated the family’s weekly intent into a more practical schedule. The interface separated the week into days and learning zones so parents could see how the plan would feel in real life.

colearn parents 05 — Daily planner showing structured learning blocks across the week.

This view helped balance structure and breathing room. Parents could create rhythm without overloading every day, and the product could support both planned learning and flexible family routines.

The resource discovery area extended the app beyond scheduling. Parents could search for programs, classes, and learning providers directly from the product, making the app feel more like a learning ecosystem than a task manager.

colearn parents 07 — Resource marketplace for finding programs by subject and learner fit.

This mattered because planning and discovery are connected. A parent might notice a gap in the week, search for a science resource, and then turn that resource into a scheduled learning block.

The broader Discover experience supported a more open-ended browsing mode. Parents could explore featured programs, categories, and activities before deciding what belonged in a learner’s plan.

colearn parents 08 — Discovery view for browsing featured and category-based learning programs.

I also designed visibility into what learners were actually doing. The activity feed surfaced completed blocks, help requests, milestones, feedback, and in-progress work so parents could stay informed without interrupting the learner experience.

colearn parents 09 — Activity feed showing completed work, help requests, milestones, and feedback.

This closed the loop between planning and reality. Parents could see whether the schedule was working, whether a learner needed support, and whether progress was happening across subjects.

The app also needed a clear family management layer. Parents were not managing one generic student, they were managing multiple learners with different ages, grade levels, needs, and schedules.

colearn parents 11 — Learner management view for multiple children in one family account.

Because this was a child-centered education product, trust and control were part of the core experience. Privacy, content filtering, screen time, and data controls had to feel accessible, not buried.

colearn parents 13 — Privacy and safety controls for parent-managed learning settings.

Together, these supporting screens made the product feel complete. The app was not just a planner. It was a parent operating system for coordinating learning, resources, learner progress, and family-level controls.

Outcome

The Parents App created a calmer operating model for family-led education.

Instead of making parents assemble the learning experience from scattered tools, the app gave them one place to plan, monitor, adjust, and discover.

diagram parent 03 — The final system unified planning, visibility, resources, and parental control.

The design supported multiple learners, flexible scheduling, reusable learning blocks, resource discovery, and parent confidence. It also made the broader Colearn ecosystem more coherent by connecting planning, discovery, activity, and family management into one experience.

The strongest outcome was clarity. Parents could see what was happening, what needed attention, and how each learner was progressing without losing the flexibility that made the learning model valuable.