a developer's working notebook · vol. 1

Mustafa Noori

AI engineer
→ generative image + video pipelines.

IstanbulAI + full-stackArabic / English

currently —

prompt compilation + model routing

at Designar.AI ↗

Hello world!

02 · about

page of notes.

I build the layer between what a person wants and what a model actually returns — prompt compilation, reference-image routing, and the queue and retry logic that keeps a flaky model from taking the interface down with it.

At Designar.AI that means turning structured product data into model-ready prompts for fashion photography and catwalk video, in Arabic and English. Before that I was a front-end developer, and still am — which is why I can ship the whole path instead of handing half of it off.

Eleven years passed between the computer-engineering degree and the engineering job. I'm late on purpose and I'd take the detour again.

on the desk →

A logo-generation benchmark — 18 fixtures, and a router that knows which model breaks on Arabic.

coffee count today:
3 ☕ ☕ ☕

what I'm looking for

AI engineering where the model is the product, not a feature bolted on
a team that reviews prompts the way it reviews code
work that touches Arabic, or any script the defaults handle badly
(bonus) someone to argue with about evals

03 · stack

now, next, and the longer arc.

The through-line is generative systems — everything here either feeds a model or catches what it hands back.

cluster · 01

shipping with —

the front end, where I'm fluent — bilingual RTL apps, and the UI that makes a pipeline usable.

React 19TailwindNext.jsTypeScript

i18n · RTLTanStack Queryaccessibility

cluster · 02

learning —

the server side — job queues, streaming, and the retry logic between a flaky model and someone waiting on it.

← the API layerthe queue →↑ the data layer

Node · ExpressFastAPIPostgreSQLSSE · job queues

cluster · 03

studying —

the master's, and the R&D that spills out of it — multi-agent systems, retrieval, evaluating an output when “correct” isn't one string.

PythonMulti-agent systemsRAGPrompt evaluation

04 · work

the work.

Two builds, both solo, both about the same thing: the interesting part is never the happy path.

project · 01 of 02

Document Analysis Platform — an AI reading it so you don't have to.

document list · live search · filters · sort

→ the main view

▸ live progress: summary → sentiment → entities

▸ click-to-highlight entity tagging, filterable

▸ sentiment score with confidence, inline

2. backend

3. the interesting bit

The Hugging Face free tier is flaky — cold-start 503s, rate limits, timeouts. The real problem wasn't calling three models, it was staying usable when they don't cooperate: backoff retries, a 3-slot queue, and a "partial" status so one failure doesn't sink the other two.

the constraint, stated plainly.

role · solo · full-stack

A Next.js front end, SSE API routes, and three Hugging Face models — summarization, sentiment, NER — in one ingest-to-report pipeline.

Next.js 16PythonHugging FaceServer-Sent Events

live demo code

project · 02 of 02

Coffeeroasters — a pricing matrix you can read as a sentence.

plan builder · mid-flow

→ the main view

▸ step-by-step, one question at a time

▸ live summary sentence rewrites as you pick

▸ order-summary modal shows the monthly price

2. logic

3. the interesting bit

The sentence changes shape, not just its values. Picking "Capsule" flips "as" to "using," drops the grind clause entirely, and disables a downstream step. Keeping that readable — plus the 9-combination price — with no state library was the actual problem.

role · solo · front-end

A step-by-step plan builder with a live summary sentence and price that rewrite themselves as you choose — 3 weights × 3 frequencies, computed client-side, no backend.

Next.jsTypeScriptTailwind v4 @themea11y · keyboard + SR

live demo code

also in the notebook

…plus the client work.

Three sites shipped end to end — a nutrition coach, a coffee-equipment retailer, and a bilingual showroom for an architectural glass manufacturer. The experiments live on GitHub.

github.com/Mustapha909

05 · work & education

track record.

Two careers so far — research and writing, then engineering.

work —5 ROLES · 2 CAREERS

currently ✶

Designar.AI — Front-End / AI Engineer

DEC 2025 → PRESENT · REMOTE

I own the prompt-compilation layer — structured data in, model-ready prompts out — shared across Fashion ProShot, Mukhawar ProShot and the catwalk video pipeline I built (Gemini + Kling keyframes, stitched with ffmpeg). Now leading R&D on logo generation, routing by which model breaks least on Arabic.

Next.js · i18nGemini · Klingprompt architectureffmpeg

Freelance — Front-End Developer

SEP 2025 → PRESENT · REMOTE

Three client sites end to end in React 19 + Vite + Tailwind: a nutrition coach, a coffee-equipment retailer, and a fully bilingual showroom for an architectural glass manufacturer — context-based i18n with RTL/LTR switching on every page.

React 19 · Vitebilingual EN / AR

QafLab — Front-End Developer, Intern

JUL 2024 → OCT 2024 · MOSUL

The React/TypeScript front end for a bulk-SMS platform. The part worth naming: three-tier role-based UI gating with permission-aware routing, backed by TanStack Query across list-heavy views.

React · TypeScriptTanStack Query

Al Basheer Show — Research & Content Developer

SEP 2019 → SEP 2025 · REMOTE

Six years writing weekly episodes for a satirical news show with a multi-million Arab audience — turning complex political stories into accurate, accessible Arabic, to a fixed weekly deadline.

Arabic narrativeweekly deadline × 6 yrs

Various roles — Retail, NGO, tourism

2015 → 2019 · IRAQ & TURKEY

Relocated to Turkey and worked across sales, NGO support and tour guiding before moving back into software.

education —2 DEGREES

in progress

Beykoz University — M.Sc. Artificial Intelligence

IN PROGRESS · EXPECTED MAY 2027 · ISTANBUL

Advanced Prompt Engineering for Intelligent Agents, Data Mining, and Advanced Algorithms — the things I kept hitting at work before formally covering them.

Prompt engineeringData miningAlgorithms

Al-Hadbaa University — B.Sc. Computer Engineering

2014 · MOSUL, IRAQ

Computer organization, microprocessors, DSP, and distributed/real-time system design — a stranger foundation for prompt engineering than it sounds, and a more useful one.

the short version

one paragraph, if you're skimming.

AI engineer with a full-stack foundation, in Istanbul. I build production generative image and video pipelines for a bilingual Arabic/English design platform — prompt compilation, model routing, and the queue and retry logic underneath. Finishing an M.Sc. in AI at Beykoz, open to the right AI-engineering role.

tldr

06 · contact

inside back cover.

return to · mustafa noori

say hi —

if you're hiring →

Tell me what the model is doing in your product, and who's on the hook when it returns something wrong. The prompt layer, the routing, the evaluation — that's where I'm happiest. Non-Latin scripts a plus, not a problem.