shahzaib.builds

● Pre-med → AI · Lahore, Pakistan

I was supposed to be a doctor.
Instead I build AI.

I'm Shahzaib — AI automation engineer at Automaxion, educator, and self-taught Linux convert. Four Python bootcamps. A co-founded AI club. A BS in AI from IUB. Now shipping production agents, voice bots, and pipelines for clients across three continents.

See the pivot →or jump to what I've built
Shahzaib Hassan

The Path Not Taken

Two careers.
One person.
A five-month decision in between.

◌ if I had stayed
year
● what actually happened

  1. Move to Bahawalpur

    FSc pre-medical · biology, chemistry, physics

    182018

    —

  2. FSc complete

    Pre-med track. Frogs dissected, organic reactions memorized.

    202020

    5–6 months of research

    Reading everything I could find about what to do next.

  3. The fork

    Pre-med future vs a degree no one in my town had heard of.

    212021

    BS Artificial Intelligence, IUB

    Started from zero. Classmates had been coding since high school.

  4. —

    222022

    Ubuntu, daily, for 2 years

    A senior recommended it. It broke things; I fixed them. Stopped fearing the terminal.

  5. —

    232023

    Neurafinity Club, co-founded

    Plus the first of four Python bootcamps. Teaching forced understanding.

  6. —

    242024

    TA for the AI certificate course

    Taught the second batch of the same course I’d just finished — ML, deep learning, computer vision.

  7. —

    252025

    Hired by Automaxion · 7th semester

    Before I’d graduated. Production AI for real clients.

  8. —

    262026

    Graduated · CGPA 3.65

    Outperformed peers who’d been coding since school. Still rebuilding LinkedIn from zero.

I didn't inherit this path. I researched it for five months and chose it.

— written from Ahmadpur East to Lahore

What I built after the pivot

Five systems. Real clients.

Production work, scrubbed of client names. Click lens on any card to see the medical-school analog — the same problem in a different career.

  • 01build

    Autonomous Social Media System

    Social posting that runs itself.

    The client wanted to post on social media consistently but never had the time. So I built a system that does the whole thing without anyone touching it. It comes up with content ideas, writes the posts, and publishes them on schedule. The hard part was getting AI-written content to actually sound like the brand and not like a robot. The pipeline uses Make.com to coordinate Airtable and a few AI APIs, each one handling a different step.

    Make.comAirtableAI APIsSocial Media APIs
  • 02pipeline

    Cold Outreach Pipeline

    Personalized cold email on autopilot.

    A full cold-email pipeline from start to finish. You feed it a list of prospects, and it generates personalized email sequences and sends them through Instantly. Follow-ups happen automatically based on whether someone opened or replied. The whole thing runs on Airtable as the data layer with Make.com handling the orchestration. The challenge was getting the personalization right so emails actually felt written by a human.

    AirtableMake.comInstantlyAI APIs
  • 03build

    Data Enrichment Dashboard

    A data enrichment dashboard built from scratch.

    No automation platform for this one. A full Next.js app I built with custom API integrations. You give it a company name, and it runs through multiple stages: search, company enrichment, and detail extraction from third-party data sources. Everything shows up in a clean dashboard. The client needed complete control over their data pipeline, and no off-the-shelf tool gave them that. So I built it from scratch.

    Next.jsCustom APIsData PipelineReactTypeScript
  • 04pipeline

    Psychological Assessment Platform

    Clinical assessment turned into software.

    A psychologist had an 18-question assessment for measuring decision stability. They wanted it automated. I built the pipeline: user fills a Typeform, it triggers a custom scoring algorithm, generates a personalized PDF report, and delivers it through ActiveCampaign with follow-up sequences. The tricky part was getting the scoring exactly right. The algorithm had to match what the psychologist would calculate by hand, every edge case included.

    TypeformCustom AlgorithmPDF GenerationActiveCampaign
  • 05build

    AI Teaching Assistant for Long-Form Documents

    Upload a document, get an AI teaching assistant.

    Built for an internal training need. You upload a PDF or Word doc, and the system breaks it into chapters and generates teaching slides. Each slide gets AI-narrated voice explanations through ElevenLabs, plus a quiz after each section. The hard part was handling completely different document structures and still producing slides that made sense. Not every document is organized the same way, so the parsing had to be flexible.

    ElevenLabsAI APIsPDF/DOCX ParsingQuiz Engine

What I work in

Six clusters.
Each one rhymes with something I almost learned.

Automation

Like building a treatment protocol — same input, predictable outcome.

  • ·n8n (self-hosted)
  • ·Make.com
  • ·Zapier
  • ·Airtable
  • ·Instantly
  • ·ActiveCampaign

AI agents & LLMs

Differential diagnosis at scale — ask the right questions, narrow the answers.

  • ·OpenAI
  • ·Claude
  • ·Mistral
  • ·CrewAI
  • ·Agno
  • ·Function calling

Voice AI

The bedside manner. Tone and timing matter more than the words.

  • ·VAPI
  • ·Retell
  • ·Bland AI
  • ·ElevenLabs

Engineering

Anatomy of a system: every part connects, nothing is decoration.

  • ·Python
  • ·TypeScript
  • ·Next.js
  • ·React
  • ·Node
  • ·Postgres

Infrastructure

Like running your own pharmacy — you stock it, you maintain it, you own it.

  • ·Linux / Ubuntu
  • ·Docker
  • ·Nginx
  • ·Self-hosted VPS
  • ·Hetzner
  • ·DigitalOcean

Teaching

Residency rounds: you learn it by teaching it to someone newer.

  • ·4 Python bootcamps
  • ·AI certificate TA
  • ·Neurafinity workshops
  • ·YouTube lectures

What I taught while I learned it

Teaching forced me to actually understand things.

I co-founded the Neurafinity Club at IUB, ran four online Python bootcamps for juniors and students, and served as teaching assistant for the second batch of a 10-month AI certificate course — the same course I had just completed in the first batch.

You can't explain what you don't know. So I went deep on the parts I needed to teach: classical ML, deep learning, computer vision, then later automation and agentic AI. The bootcamps had no marketing — students kept signing up because the previous cohorts told them to.

I'm still teaching. Most of the writing on /blog is the stuff I wish someone had explained to me when I was figuring it out.

4

Python bootcamps taught

10mo

AI certificate course TA

3.65

CGPA, BS AI · IUB

PM

Laptop Scheme awardee

Writing

What I've been figuring out.

all writing

Available for

Selective freelance + consulting work.

Three things I do well. If your problem rhymes with one of them, email me.

  • 01

    Workflow Automation

    n8n, Make.com, Zapier. End-to-end pipelines that actually run.

  • 02

    AI Voice Agents

    VAPI, Retell, ElevenLabs. Inbound, outbound, in your stack.

  • 03

    Custom AI Applications

    Next.js + Python + LLM APIs. Built from scratch when no platform fits.

What I'm open to

Scholarships.
Research collaboration.
Freelance.
A good email.

I read every message. Email is best. If you're a scholarship reviewer, recruiter, or want to teach together — say hi.

shahxeebhassan@gmail.com

elsewhere