01 / 05 · LIVE IOS PRODUCT
SHIPPED JULY 2026
A live iOS product that turns photographed local timetables into editable schedules, adds anomaly checks and supports dependable daily tracking.
103 DAYS TO THE APP STORE~500K ORGANIC LAUNCH VIEWS
AI AND AUTOMATION BUILDER
TAREK
ABDELDAYEM
I direct frontier AI systems, verify their output and ship useful products end to end.
British citizen · Fluent Arabic & English · Open to relocation
Selected work
SELECTED WORK
My selected work.
Selected projects across product, AI, data and automation, from live apps to tools built for real administrative work.
02 / 05 · FINAL-YEAR COMPUTER-SCIENCE PROJECT
UNIVERSITY OF LIVERPOOL · COMP390
A support-triage system combining deterministic checks, structured AI analysis and explicit human-approval gates.
47 PASSING TESTSHUMAN APPROVAL BY DESIGN
03 / 05 · RELATIONAL DATA SYSTEM
SYNTHETIC DATASET · REPRODUCIBLE SQL
A relational commerce data system designed around typed constraints, analytical views and reproducible SQL queries.
8 CONNECTED TABLES2 ANALYTICAL VIEWS
Revenue by category: delivered orders, net of discounts
SELECT p.category,
ROUND(SUM(oi.quantity * oi.unit_price_at_purchase
- oi.discount_amount), 2) AS net_revenue
FROM order_items AS oi
JOIN orders AS o ON o.id = oi.order_id
JOIN products AS p ON p.id = oi.product_id
WHERE o.status = 'delivered'
GROUP BY p.category
ORDER BY net_revenue DESCVERIFIED OUTPUT
Books6,857.80
Clothing6,324.86
Toys5,839.44
SYNTHETIC DATASET · GBP
SHIPPED QUERY · LIVE-VERIFIED OUTPUT · 8 TABLES · 2 VIEWS
04 / 05 · PRODUCTION AUTOMATION
TWO SHIPPED FLOWS · GRAVITURE
Two shipped n8n systems behind my agency: a research pipeline that turns raw search results into typed, evidence-bound lead records, and a proposal pipeline that turns a brief into a client-ready deck.
TWO PRODUCTION FLOWSNO INVENTED FIELDS
PIPELINE
- SEARCHApify · Google results553 results
- SCRAPEFirecrawl · page content30 per run
- ANALYSEGPT · typed schema47 fields
- SCOREIntent and fit0 to 100
- WRITEAppend to sheet1 row per lead
QUALIFIED
entity_typebusiness
is_prospecttrue
industryDental practice
pain_pointNo online booking path
automation_opportunityMissed-call recovery
intent_signalmedium
lead_score78
confidence82
SYNTHETIC SAMPLE · REAL SCHEMA
RESEARCH AND PROPOSAL FLOWS · 47-FIELD RECORD · ENTITY GATE
05 / 05 · CLIENT WORK · UNIVERSITY FIELDWORK
REGISTRATION + HEALTH WORKFLOW
Two tools built for a university lecturer, turning field-course administration into structured rosters, visible follow-ups and ready-to-use documents.
TWO COMPLETE WORKFLOWSLOCAL HEALTH-DATA PROCESSING
01 / REGISTRATION02 / HEALTH WORKFLOW
FIELD COURSECOHORT A
Every group.
One clear roster.
STUDENTGROUP
Sam Example01
Alex Other01
Taylor Sample02
FORM RESPONSES → EXCEL ROSTER
LOCAL DOCUMENT ENGINE
Responses in.
Files ready.
PDFIndividual questionnaires↗
CSVParticipant list↗
HTMLStudent overview↗
PROCESSED ON DEVICE↓ ZIP
REGISTRATION → ROSTER · RESPONSES → DOCUMENT PACK · FICTIONAL DATA
ABOUT
I use AI as a production system, not as a substitute for judgment.
I am a computer science graduate who works across product direction, AI orchestration, data, testing, design and distribution. I do not treat model output as finished work: I set the brief, shape the context, inspect failures and keep iterating until the result is coherent and usable.
Rukna is the clearest proof of that approach: I took it from a conversation to a live App Store product, owning the product direction, interface, extraction workflow, backend, testing, launch and early distribution. My support-triage project taught me to constrain and evaluate AI rather than trust it blindly. CommerceLens strengthened the relational data foundations beneath that work.
The current chapter is AI automation. Inside Maker School I completed a six-hour n8n course and now build automations for Graviture, my own AI agency, including a lead intelligence engine that turns scraped prospect data into typed, evidence-bound sales intelligence and an LLM pipeline that converts it into personalised client proposals. I also delivered two tools for a university lecturer, covering field-course group registration and local health-document processing. Alongside that I am studying persuasion through Northwestern's Leadership Through Social Influence course.
BSc Computer Science
72% · First Class
- British citizen
- Fluent Arabic and English
- Open to relocation