Skip to work

00 / Index

Software engineer
Backend, AI & product engineering

Marrakech, Morocco
31.6295° N, 7.9811° W

Local
Open to work

  • 01Backend systems
  • 02AI agents & automation
  • 03Products from 0 → 1

I turn unclear ideas into working systems — the services, permissions and agent workflows underneath, and the product people use on top.

View selected workGitHub ↗Download CV

Taha Koulal

Scroll — systems under the surface

Systems under
the surface.Products
above it.

01 / Selected work

Read from the system up.

Five projects. For each: what had to work underneath, and what it made possible on top.

  1. 01Factory
  2. 02DPRO
  3. 03Vamo
  4. 04Transcendence
  5. 05FIT

01 / 05 — Multi-agent AI project factory

Factory

An agent-based delivery system where ideas are evaluated, delegated and built by small, specialised teams of AI agents.

Role
Architecture and system design
Stack
Claude Code · MCP · Agent orchestration
Fig. 01 — Delegation graph
Persistent state · audit logIncoming ideaCEO agentevaluate · delegateCTO · mode 1CTO · mode 2CTO · mode 3SandboxFocused build agentsPermission gateMilestone reviewSLA escalationMilestone shipped

01.1 — Context

A CEO agent evaluates incoming ideas, then delegates execution to specialised CTO modes that coordinate focused build agents.

01.2 — Problem

Letting agents execute projects takes more than prompts. Without clear authority, permissions and accountability, execution stops being predictable.

01.3 — What I built

  1. 01The delegation model: CEO agent → CTO modes → focused build agents.
  2. 02Permission gates, milestone reviews and SLA-based blocker escalation.
  3. 03Persistent state, audit logs and sandboxed execution.

01.4 — System

Small, specialised agent teams instead of one general agent — modelled for reliability, accountability and deterministic project execution.

02 / 05 — Business opportunity platform

DPRO

A production platform that carries each business opportunity through sales, technical evaluation, costing, sourcing and delivery.

Role
Software engineering intern — contributor to a production codebase
Stack
Next.js · Supabase · RBAC
At
PHOVA Technology
Fig. 02 — Opportunity lifecycle
S.01SalesS.02TechnicalevaluationS.03CostingS.04SourcingS.05DeliveryOpportunityWorkflow rulesNotificationsSalesEngineeringSourcingManagementRole-based accessBefore — multi-step screenAfter — aligned to responsibilitySalesEngineeringSourcing

02.1 — Context

Opportunities move between sales, engineering, sourcing and management. Each team owns a different part of the same record.

02.2 — Problem

Permissions, notifications and screens have to follow how the work actually moves between people — not duplicate it.

02.3 — What I built

  1. 01Built and improved RBAC, notifications and workflow rules.
  2. 02Opportunity management and complex technical interfaces, shaped with business stakeholders.
  3. 03Simplified multi-step technical screens by removing duplicated information and aligning them with real operational responsibilities.

02.4 — System

Next.js and Supabase, with access control and workflow rules mapped to operational responsibilities.

03 / 05 — Football identity mobile product

Vamo

A mobile product that gives football players a persistent identity across matches, teams and tournaments — including a Football Passport.

Role
Designed and built — product structure, core flows, data access
Stack
React Native · Supabase · Row-level security
Live
vamo-l.vercel.app ↗
Fig. 03 — Identity graph
Team 1Team 2MatchAttendanceTournamentPhone · teammates onlyRLS policyPlayerFootball Passport

03.1 — Context

Players, teams, matches and tournaments form a dense web of relationships. Vamo turns it into a persistent profile history.

03.2 — Problem

The network has to be discoverable, while personal data stays visible only to the right people.

03.3 — What I built

  1. 01Product structure and core flows from zero: discovery, match and tournament creation, attendance, profile history.
  2. 02Persistent player identities, teams, tournaments and the Football Passport.
  3. 03Privacy-aware Supabase RLS, including teammate-only phone visibility and secure player-data access.

03.4 — System

React Native client on Supabase. Row-level security policies decide who can read which player data.

03.5— Livevamo-l.vercel.app

Visit landing page (opens in a new tab)

04 / 05 — Real-time multiplayer platform

Transcendence

A multiplayer Pong platform with authentication, live messaging and synchronised game state.

Role
Auth, live messaging, real-time game state and session behaviour
Stack
React · TypeScript · WebSockets
Fig. 04 — Event stream
Client AServerClient BClient AWebSocket srvClient Bauthsessioninputgame statechatchatsyncsync20+ concurrent games

04.1 — Context

Game state, chat and user interactions change at the same time, for many players, across many games.

04.2 — Problem

Every client has to agree on what is happening — the ball, the score, the conversation — while events keep arriving.

04.3 — What I built

  1. 01Authentication, live messaging and synchronised game state.
  2. 02Real-time frontend state and game-session behaviour supporting more than 20 concurrent games.
  3. 03Event-driven communication to keep multiplayer state, chat and interactions in sync.

05 / 05 — AI wardrobe and outfit app

FIT

Catalogue the clothes you already own once. Get a complete, context-aware look each day — instead of another purchase.

Role
Product concept and recommendation structure
Stack
React Native · Recommendation system
Status
Product concept
Fig. 05 — Recommendation model
Wardrobe itemsWeatherSkin toneBody shapeColour compatibilityPreferencesContextComplete lookReuse, not purchase

05.1 — Signals

Wardrobe items, weather, skin tone, body shape, colour compatibility and personal preferences.

05.2 — Output

Daily outfit recommendations built from wardrobe reuse rather than unnecessary purchases.

02 / Experience

From the surface down.

Production work on top. The interactive and systems foundations it stands on, underneath.

  1. L.01 — Surface

    PHOVA Technology

    Software Engineering Intern

    Production

    Delivered backend and product features inside an existing codebase, translating operational requirements from sales, engineering, sourcing and management into usable workflows.

    Worked across backend behaviour, access control, notifications, workflows and product UX, coordinating feedback with non-technical stakeholders.

    • Backend
    • Access control
    • Workflows
    • Product UX

  2. L.02 — Interactive

    UM6P — IDC Morocco

    VR Development Intern

    VR / Interactive Technologies

    Developed an immersive virtual-visit experience from prototype to functional delivery, including interactive 3D environments and navigation.

    • Unity
    • C#
    • 3D navigation
    Fig. L.02 — Virtual visit, stereo model
    ABC
    Room
    A · Entrance
    Pos
    0.0, -4.5
    Head
    —
    Frame
    —

    Waypoint 01 / 04

    Model, not a capture · drag or arrow keys to look · click a ring or press 1–4 to jump · gaze at ◇ to open info

  3. L.03 — Foundation

    42 Network (1337)

    Common Core — in progress

    Software Engineering

    Validated ft_irc, Minishell, Philosophers, ft_printf, Libft and 10+ projects — systems programming from the ground up.

    • ft_irc
    • Minishell
    • Philosophers
    • ft_printf
    • Libft

03 / System

The stack, in cross-section.

Grouped by where each piece sits relative to the surface. Select a technology to trace it back to the work.

01  Product engineering

Above the surface — what people touch

02  Backend & systems

Under the surface — state, data, transport

03  AI & automation

Orchestration — agents that act on the system

Also — Unity · C# (VR internship, UM6P)

Method

How I approach a build.

  1. i

    Start with the workflow

    Begin from the user and the business workflow, not the stack.

  2. ii

    Make ambiguity explicit

    Translate unclear needs into explicit priorities.

  3. iii

    Secure the foundations

    Clear permissions, data boundaries, auditability and review gates.

  4. iv

    Accelerate with AI

    Use AI to move faster while engineering judgment and product quality stay central.

Engineering strengths

  • 010-to-1 product development
  • 02Architecture and technical scoping
  • 03RBAC, security and data boundaries
  • 04Workflow and systems design
  • 05Cross-functional collaboration
  • 06AI-assisted delivery with review gates
Portrait of Taha Koulal, smiling, in a white t-shirt
COMPout

04 / About

I like turning unclear ideas into working systems.

I came to software from two directions: systems — C, Unix and networking at 1337 — and interactive work, building a VR virtual visit at UM6P.

Now I work where those meet. Access control, workflows, real-time state and agents underneath; flows and interfaces on top. I use AI to move faster, with review gates so judgment stays in the loop.

Based in
Marrakech, Morocco
Studying
42 Network (1337)
Languages
Arabic — Native English — Professional French — Intermediate
Open to
Full-time & early-stage product roles

05 / ContactAvailable for full-time and early-stage product opportunities

Have something unclear? Let's make it work.

Write to

tkoulal.21@gmail.com