Colearn Homeroom

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 teacher operations app that helped homeroom leads monitor families, attendance, onboarding, and learning progress.

Skills applied:

Visual Design Interaction Design Research Information Arch

Homeroom teachers needed more than a roster. They needed an operational view of every family, learner, attendance signal, onboarding status, and support need across a flexible learning program.

I designed the Homeroom app as the teacher-facing layer of the Colearn ecosystem, helping educators monitor families, identify learners who needed attention, manage attendance, and keep communication consistent.

The Problem

Teachers were responsible for supporting many families, but the signals they needed were scattered across attendance records, onboarding steps, learner profiles, and family communication.

In a flexible education model, teachers are not only classroom instructors. They become guides, monitors, coordinators, and support partners for families navigating individualized learning paths.

That creates a different operational problem. A teacher may need to know which families are enrolled, which learners are below attendance thresholds, which resources are assigned, which onboarding steps are incomplete, and which families need follow-up.

diagram homeroom 01 — Teachers needed one place to see families, risk signals, and support needs.

The challenge was visibility. Without a unified view, teachers could spend too much time searching for signals instead of acting on them.

The product also had to support trust. Families needed communication and support, but teachers needed enough operational structure to identify problems early and follow up consistently.

Solution

I designed Homeroom as a teacher command center, combining roster management, attendance intelligence, family context, onboarding progress, and communication controls.

The dashboard gave teachers a high-level operating view of their homeroom. It surfaced total families, learners, weekly minutes, learners needing attention, attendance trends, curriculum distribution, alerts, and onboarding progress.

colearn homeroom 01 — Dashboard view summarizing families, attendance, curriculum, alerts, and onboarding.

This overview helped teachers move from reactive support to proactive guidance. Instead of waiting for a family to reach out, the teacher could quickly identify which learners or families needed attention.

The roster view provided the administrative foundation. Teachers could scan family names, contact details, locations, and learner counts from a clean table designed for quick lookup.

colearn homeroom 02 — Families roster showing contact details, locations, and learner counts.

The roster was not just a list. It was the entry point into deeper family context. From there, teachers could review an individual family’s learning strategies, interests, assigned resources, and progress signals.

colearn homeroom 03 — Family detail view connecting progress, learning strategies, and resources.

This family-level view mattered because support is contextual. A teacher could understand what a family was working on, what they cared about, and which resources were part of their learning plan.

diagram homeroom 02 — Homeroom connected family context with teacher action.

Attendance was one of the clearest operational signals. I designed the attendance view to separate learners who required attention from the full learner list, making it easier for teachers to focus on exceptions first.

colearn homeroom 04 — Attendance view highlighting learners below required weekly minutes.

This helped teachers avoid scanning every learner manually. The interface emphasized thresholds, exceptions, and export actions so attendance could become a support workflow, not just a compliance table.

The settings layer gave teachers control over how their homeroom operated. They could configure term dates, family capacity, approval behavior, and welcome messaging.

colearn homeroom 06 — Homeroom settings for term dates, enrollment capacity, and family onboarding.

These controls made the product adaptable to different homeroom structures. Teachers could manage enrollment rules and communication expectations without relying on hidden admin workflows.

Attendance configuration extended this control further. Teachers could define minimum daily minutes by grade tier, set alert thresholds, choose export formats, and enable automatic low-attendance flags.

colearn homeroom 08 — Attendance thresholds and alert settings for different grade levels.

This was important because attendance expectations are not the same for every learner. Younger students, middle grades, and older students need different thresholds and different levels of monitoring.

Communication settings closed the loop. Teachers could configure family reminders, progress updates, weekly attendance summaries, and email signatures from one place.

colearn homeroom 09 — Communication settings for family reminders and weekly progress updates.

Together, these workflows positioned the teacher as an informed guide. The app gave them visibility, context, thresholds, and communication tools without turning the experience into a heavy administrative system.

Outcome

The Homeroom app gave teachers a clearer operating model for supporting families before small issues became larger problems.

Instead of managing families through disconnected records and manual follow-up, teachers had one workspace for monitoring progress, attendance, onboarding, family context, and communication.

diagram homeroom 03 — The final system turned teacher oversight into a proactive support loop.

The design helped teachers identify learners needing attention, understand family context, manage attendance expectations, and keep families informed. It also strengthened the Colearn ecosystem by connecting the teacher layer to the parent and learner experiences.

The broader outcome was operational clarity. Parents had planning and oversight tools. Learners had a focused workspace. Teachers had the visibility and controls needed to support the entire homeroom.