import torch from fastapi import FastAPI from pydantic import BaseModel class Config: model = "gemini-2.5" batch_size = 32 lr = 3e-4 epochs = 100 app = FastAPI() @app.post("/predict") async def predict(req): features = extract( req.data, pipeline="v3" ) return model(features) # ── data pipeline ── SELECT region, COUNT(*) as trips, AVG(duration) as avg_t FROM rides WHERE status = 'done' GROUP BY region ORDER BY trips DESC; async def train(): for epoch in range(N): loss = step(batch) if loss < best: save(model) best = loss # ── config ────── [fikia] name = "nzela-api" region = "af-east-1" runtime = "python3.11" env: DB_HOST: postgres REDIS: cache:6379 MODEL_PATH: /v3/ def transform(df): df = df.dropna() df["lat"] = to_rad( df.latitude ) return normalize(df) # ── deploy ────── stages: - build - test - ship class Agent: def __init__(self): self.memory = [] self.tools = load() async def run(self, task, ctx=None ): plan = reason(task) for step in plan: r = execute(step) self.memory.add(r) return synthesize( self.memory ) # ── metrics ───── latency_p99: 142ms throughput: 2.4k rps accuracy: 0.94 uptime: 99.97% router.post("/api/v2") async def handler(body): validated = parse(body) result = await pipe( validated, steps=[ clean, embed, classify ] ) return {"ok": True}

001 002 003 ··· 007 008 ··· 014 015 016 ··· 021 022 ··· 028 029 030 ··· 035 036 ··· 041 042 043 ··· 048 ··· 052 053 ··· 058 059 060 ··· 064 065 ··· 070 071 ··· 076 077 078 ··· 083 084 ··· 089 090 ··· 094 095 ··· 100

Powering Connected Experiences

Fikia

The technology team behind
ambitious businesses.

Start a projectSee our products

Layer 1.0 / Build

What we build

A working menu of what we do. Bring the problem. We work out the shape.

Headline

Software Development

Web apps, mobile apps, internal tools. From prototype to production-grade systems.

Automation

Workflows that run themselves. Data sync, scheduled tasks, AI-assisted operations.

Data and Machine Learning

Make sense of what you have. Dashboards, models, predictions, decision support.

App Testing

We test your software so you can ship with confidence. Manual and automated.

Don't see it here?

If we can't build it, we know who can.

Our principle

We close the distance between an idea and the running system it becomes.

0

Products
in production

0+

Custom builds
shipped

0

Cookie-cutter
solutions

Layer 2.0 / Run

Products we own

An operations platform for businesses that run on processes.

A point-of-sale system for modern retail and hospitality.

See all products

Layer 3.0 / Reach

Where the work lives.

A scattered atlas of recent builds. Each one shipped to a real client.

01

2025EventsUG

Aftersun Ticketing

A bespoke ticketing platform for Aftersun events. Designed for high-volume on-the-day check-in, reliable mobile experience, and clean reporting after the gate closes.

ClientAftersun

TicketingEventsMobile

02

2025OperationsUG

Tushiya Automations

A suite of custom workflow automations connecting Tushiya's day-to-day tools. Manual back-office steps replaced with reliable, scheduled, observable pipelines.

ClientTushiya

AutomationWorkflowsIntegrations

03

2024ApplicationUG

POATE

A custom application delivered for Eyeopener. End-to-end build from discovery through deployment.

ClientEyeopener

Custom BuildApplication

Reach further.

Tell us what you're building. We'll show you the fastest path to it.

Start a project