Colearn Homeroom Admin

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

Colearn Homeroom Admin

A school admin app that unified enrollment, homerooms, attendance, staff roles, and operational reporting.

Skills applied:

Visual Design Interaction Design Research Information Arch

Flexible learning programs create operational complexity at the school level. Admins need to coordinate families, homerooms, teachers, attendance requirements, enrollment capacity, staff access, and reporting without relying on disconnected spreadsheets or manual follow-up.

I designed the Homeroom Admin app as the school-wide control layer for the Colearn ecosystem. It gave administrators visibility across the full program while keeping day-to-day teaching and family support delegated to homeroom staff.

The Problem

School admins needed to manage a distributed learning program, but the most important operational signals lived across separate workflows.

At the admin level, the challenge was not one family or one learner. It was the full network: enrolled families, pending applications, active homerooms, staff roles, attendance compliance, and reporting expectations.

Without a dedicated admin layer, school leaders could lose visibility into capacity, learner activity, attendance risk, staff permissions, and whether homerooms were operating consistently.

diagram admin 01 — Admins needed one place to manage school-wide operations and risk.

The product also needed to preserve separation of responsibilities. Teachers needed focused homeroom tools. Parents needed family planning tools. Learners needed a simple daily workspace. Admins needed a higher-level control system without interfering with every classroom-level action.

Solution

I designed Homeroom Admin as the governance and operations layer for the full Colearn learning network.

The dashboard provided a school-wide summary of families, learners, active homerooms, average attendance, enrollment status, recent activity, family locations, and learners needing attention.

colearn admin 01 — Admin dashboard showing enrollment, attendance, homerooms, locations, and attention signals.

This view helped admins understand the health of the program at a glance. Instead of inspecting every homeroom manually, they could see operational trends and identify where intervention might be needed.

Enrollment became a dedicated workflow because onboarding families is one of the highest-friction parts of a flexible education program. The enrollment roster showed family status, learner counts, reminders, and actions like enrolling or nudging families.

colearn admin 02 — Enrollment roster showing family status, learner counts, reminders, and actions.

This separated enrollment from ongoing homeroom management. Admins could focus on pending families, missing learner setup, waitlist rules, and application status without cluttering teacher workflows.

Homeroom management provided the bridge between school-level oversight and teacher-level support. The homeroom roster showed each homeroom, assigned teacher, family counts, learner counts, and recent activity.

colearn admin 03 — Homeroom roster showing teachers, families, learners, and recent activity.

From there, admins could inspect one homeroom in detail. This made it possible to understand how families were distributed and whether a specific teacher’s homeroom needed support.

colearn admin 05 — Homeroom detail view showing assigned families and contact context.

The expandable family rows added another layer of operational visibility. Admins could drill into learner attendance within a homeroom without leaving the broader management context.

colearn admin 06 — Expanded family row showing learner attendance details inside a homeroom.

Roles and permissions were a critical part of the design.

diagram admin 02 — Admin workflows connected school structure with operational action.

The product needed to support different staff types without giving every person full administrative control.

colearn admin 07 — Roles and permissions view defining staff access across admin workflows.

The permissions matrix made governance visible. Admins could understand who could view dashboards, manage enrollment, edit homerooms, track attendance, manage roles, and access staff records.

The staff directory complemented the role system. It gave admins a practical way to see staff members, assigned roles, active status, last activity, and invitation state.

colearn admin 10 — Staff directory showing roles, status, activity, and staff management actions.

The settings layer handled the operational rules behind the system. Enrollment settings let admins define capacity, enrollment windows, waitlist behavior, and approval policies.

colearn admin 12 — Enrollment settings for capacity, windows, waitlists, and approval policies.

Attendance settings handled compliance complexity. Admins could configure requirements by state and grade level, then define alert thresholds for learners who fell below expectations.

colearn admin 13 — Attendance settings for state rules, grade goals, and alert thresholds.

Finally, data and export tools made the system accountable. Admins could configure export formats, anonymization, quick exports, backups, and retention.

colearn admin 16 — Data export settings for rosters, attendance, staff, and homeroom reports.

Together, these workflows created a control layer that supported school operations without overwhelming teachers, parents, or learners with admin complexity.

Outcome

The Homeroom Admin app gave school leaders a coherent way to operate, govern, and scale a flexible learning program.

Instead of managing enrollment, staff permissions, attendance rules, and homeroom visibility through disconnected tools, admins had one workspace for school-wide oversight.

diagram admin 03 — The final system unified school oversight, governance, reporting, and intervention.

The design created a clearer separation between admin work, teacher support, parent planning, and learner execution. Admins could monitor the entire program, while each user group still received a focused experience for their own responsibilities.

The broader outcome was scale. The Colearn ecosystem now had a school-level operating layer capable of supporting more families, more homerooms, more staff roles, and more compliance requirements without collapsing into manual coordination.