# EASS — Engineering of Advanced Software Solutions · Yossi Eliaz

Canonical page: https://yossieliaz.netlify.app/eass/

TEACHING · SYSTEMS · PRODUCT · GTM

**Engineering of Advanced Software Solutions** is a two-part HIT course about end-to-end ownership. **Part A:** one student owns a software system from problem to deployment. **Part B:** a team expands that ownership to users, operations, measurement, and distribution.

PART A · INDIVIDUAL

## Own the whole system.

Each student takes an idea to a running, testable product and practices architecture, interfaces, reliability, deployment, and end-to-end ownership.

Problem → Architecture → API + data → UI → Tests → Deploy → E2E demo

**Core:** Python & uv · Git/Linux · HTTP/APIs · FastAPI · persistence/migrations · frontend · Docker/Compose · testing/CI · auth/security · async work · caching/queues · cloud/AI · observability.

PART B · TEAM / STARTUP OPERATING LOOP

## Own the operating loop.

Teams choose a real problem, find users, ship, operate the product, measure what happens, and iterate from evidence. Product, engineering, ML, reliability, and GTM become one operating loop.

Problem → Users → MVP → Ship → Measure → Talk to users → Iterate

**Core:** problem selection · customer discovery · product scope · team ownership · production operations · analytics/experiments · AI/ML where useful · reliability/security · pricing/positioning · distribution/GTM · weekly shipping · metrics · demo day.

[Public Part B / GTM update](https://www.linkedin.com/posts/yossi-eliaz_gtm-engineering-what-it-is-and-how-to-hire-activity-7462378088744751105-OPgE)

## Selected Part A systems

A verified sample across cohorts showing progression from full-stack foundations to AI-native systems.

AI-NATIVE FULL STACK

### SousChef

FastAPI + Streamlit recipe system with AI extraction from text/images/URLs, JWT auth, Redis-backed background work, Docker Compose and Playwright E2E.

`FastAPI` `AI` `Redis` `JWT` `Playwright`

[GitHub](https://github.com/EASS-HIT-PART-A-2026-CLASS-IX/SousChef)

MICROSERVICES + LLM

### Prompt Vault

FastAPI prompt library with SQLModel/Alembic, Redis, a separate analyzer service, Claude via Pydantic AI, Docker Compose and async refresh.

`FastAPI` `Alembic` `Redis` `Pydantic AI`

[GitHub](https://github.com/EASS-HIT-PART-A-2026-CLASS-IX/prompt-vault)

DATA PIPELINE

### Israel Flights Tracker

Scheduled flight-data ingestion with FastAPI, Streamlit, PostgreSQL, analytics endpoints and Docker Compose.

`FastAPI` `PostgreSQL` `ETL` `Docker`

[GitHub](https://github.com/EASS-HIT-PART-A-2022-CLASS-III/IsraelFLights)

FULL-STACK FOUNDATIONS

### Notes App

React frontend, FastAPI backend, MongoDB and Docker Compose—the early-course end-to-end pattern in a compact system.

`React` `FastAPI` `MongoDB` `Docker`

[GitHub](https://github.com/AnastasiaH8696/notes-app)

## Selected Part B ventures

These examples show company-level ownership in practice: users, product, operations, measurement, iteration, distribution, and the code that supports them.

AI FOOD · PRODUCT + GTM

### Fridgi

AI home-food management for inventory, recipe suggestions and shopping. The team also did customer segmentation, market research, revenue modeling, lead generation and outreach.

System → users → market → leads.

`AI vision` `consumer` `discovery` `GTM`

[Product channel](https://www.instagram.com/smartfridgi/)

MEDIA · LIVE PRODUCT

### Prizma News

A live publishing product with content, readers, distribution, and an operating public surface.

Build → publish → operate → learn.

`media` `publishing` `live product` `distribution`

[Live product](https://www.prizma-now.co.il/)

EARLY PART B · COMPUTER VISION

### Waste-contamination detection

An earlier cohort applied computer vision to contamination in waste streams and connected model output to an operational decision.

`computer vision` `waste` `ML` `operations`

Instructor-record example.

## From software systems to AI systems

AI is not a third course phase. It deepens the same ownership model: inspect the mechanisms, build a model you can understand, learn the full training system, then engineer the agent around it.

Mechanisms → Inspectable model → LM stack → Agent system

MECHANISMS FROM THE READING LIST · SUTSKEVER 30

### Implement the ideas, not just the papers

Sutskever 30 turns a foundational deep-learning reading list into 30 educational, NumPy-first Jupyter implementations—from RNNs, LSTMs, ResNets and attention through scaling laws, RAG and long-context behavior. Use it to connect paper-level ideas to code you can inspect, run, and modify.

[Sutskever 30 implementations](https://github.com/pageman/sutskever-30-implementations)

SMALL, INSPECTABLE MODEL · GUPPYLM

### Make the black box small enough to open

GuppyLM is an open-source, 8.7M-parameter Transformer trained from scratch on synthetic conversations. Its project traces the path from generated data and tokenizer through training, inference, and a browser demo. It is a teaching example, not a production model.

[GuppyLM source and notebooks](https://github.com/arman-bd/guppylm)

LANGUAGE MODELING FROM SCRATCH · STANFORD CS336

### Engineer the full language-model stack

Stanford CS336 follows the complete path from tokenization and Transformer implementation through GPU kernels, parallelism, scaling, data, evaluation, and post-training, including reinforcement learning for reasoning.

[Stanford CS336 course](https://cs336.stanford.edu/)

ENGINEERING AI AGENTS · STANFORD CS329Z

### Engineer the system around the model

Stanford CS329Z moves from retrieval, tool use, and memory to multi-agent systems, evaluation, safety, and coding agents. It makes the model one component inside a larger system whose behavior must be measured and reproduced.

[Stanford CS329Z course](https://cs329z.stanford.edu/)

**Classroom connection:** the components change, but the standard does not: define behavior, make the system runnable, evaluate it over meaningful tasks, inspect failure modes, and preserve reproducibility.

## Course infrastructure

The course is supported by reusable practice and assessment systems. Some are public; some are internal course tools.

COURSE PLATFORM · INTERNAL

### EASS Engineering Mastery

**455 questions across 34 modules** covering durable systems mental models and practical engineering.

Course-maintained practice system.

ASSESSMENT · PUBLIC

### EASS Auto-Grader

Parallel multi-repository evaluation with structured reports, code-similarity analysis, and originality checks for reproducible assessment.

[GitHub](https://github.com/zozo123/eass-auto-grader)

COURSE HUB · INTERNAL

### EASS Hub

Internal course workspace for organizing engineering resources and course material.

Private course repository.

## Teaching thesis

**Part A** teaches individual technical ownership. **Part B** expands that ownership to a team, users, operations, metrics, and distribution. **AI changes the components—not the standard of evidence.**