Available for new projects

I build AI automations that give your team its time back.

I'm Mehadi Hasan — an AI Automation Lead with 8+ years of engineering experience. I design AI-driven workflow orchestration (n8n, Make.com, LLM agents), RPA bots (UiPath, Robomotion, Playwright), web scrapers, and scalable backend systems that eliminate manual overhead for businesses.

Book a free 15-min automation audit See my work
8+
years of engineering experience
300+
clients served worldwide
70+
client workspaces migrated in one project

Case Studies

Selected Work

Real systems running in production. Each case study covers the problem, the solution, and the outcome.

Diagram of the Laravel migration platform moving Trello boards to Monday.com via REST and GraphQL APIs

Software · SaaS Migration

Trello → Monday.com Migration Platform

A Laravel platform that migrated 70+ client workspaces from Trello to Monday.com — boards, comments, attachments and all.

Laravel PHP GraphQL REST APIs +4
Read case study
Flow diagram of the AI meeting pipeline: Fireflies.ai transcripts processed by Claude and OpenAI, delivered to Notion, Monday.com, Gmail, and Slack

AI · Workflow Orchestration

Meeting → Action-Items AI Pipeline

Transcripts become notes, summaries, and owner-assigned action items on the right task board — automatically.

n8n Fireflies.ai Claude OpenAI +4
Read case study
Flow diagram of the AI follow-up agent connecting GoHighLevel leads to OpenAI-generated call, SMS, and email sequences via Twilio and ElevenLabs

AI · Sales Automation

AI Follow-Up Agent for Lead Nurturing

Contextual call, SMS, and email sequences driven by AI — triggered by how each lead actually behaves.

n8n GoHighLevel OpenAI Twilio +1
Read case study
Diagram of n8n automations bi-directionally synchronizing Monday.com client, internal, project, and task boards with Slack alerting

Automation · n8n

Monday.com Board Sync Suite

Webhook-driven n8n automations keeping client-facing, internal, project, and task boards in perfect sync.

n8n Monday.com Webhooks GraphQL +1
Read case study
Flow diagram of the short-term-rental compliance research automation using the Perplexity API to produce cited reports in Google Docs with Slack notifications

AI · Research Automation

STR Compliance Research Automation

Source-cited compliance reports generated automatically with Perplexity — research that took hours now takes minutes.

n8n Perplexity API Google Docs API Slack API
Read case study
Diagram of the Python automation using Playwright and the Spotify API to scrape and verify playlist curator contacts

Automation · Data Extraction

Spotify Playlist Curator Intelligence Tool

Playwright + Spotify API automation that compiled 3,000+ verified playlist curators — 40 weekly research hours down to minutes.

Python Playwright Spotify API
Read case study
Robomotion workflow diagram of the PG&E and SFWater utility bill automation bots showing login, PDF download, OCR, and database steps

RPA · Data Pipeline

Utility Bill Data Pipelines (PG&E + SFWater)

Unattended bots that retrieve, OCR, and archive hundreds of utility PDFs from two providers — no human in the loop.

Robomotion Tesseract OCR PostgreSQL Excel +3
Read case study
Illustration of automated bill payment workflow for the AppFolio property management platform

RPA · Property Management

Automated Bill Submission on AppFolio

A bot that files vendor bills in AppFolio for real-estate administrators — login to saved invoice in seconds.

Robomotion JavaScript AppFolio
Read case study
Architecture diagram of the Villicus monitoring system server connecting client devices to Micro800 PLCs over TCP/IP

Software · Industrial IoT

Villicus Industrial Monitoring Server

A multithreaded Python TCP server that bridges client apps and Micro800 PLCs in real time — converted from a legacy C# codebase.

Python TCP/IP Sockets Multithreading Micro800 PLC +2
Read case study
Interface concept of the clinic management system built with Laravel, Livewire, and Alpine.js

Software · Healthcare

Clinic Management System

A comprehensive Laravel + Livewire platform handling the day-to-day operations of a medical clinic.

Laravel Livewire Alpine.js MySQL
Read case study
Screenshot of the e-commerce data extraction browser extension scraping product titles, prices, and images

Browser Extension · Scraping

E-commerce Data Extraction Extension

A Chrome extension that turns product listings into clean, structured JSON — pagination, bulk import and all.

JavaScript Chrome Extension APIs DOM REST
Read case study

Software · SaaS Migration

Trello → Monday.com Migration Platform

Diagram of the Laravel migration platform moving Trello boards to Monday.com via REST and GraphQL APIs
70+
workspaces migrated
100%
auditable job history
CI/CD
AWS + GitHub Actions

The problem

Get Levrg needed to move 70+ client workspaces from Trello to Monday.com. Manual migration meant recreating every board, card, comment, and attachment by hand — weeks of error-prone work per batch, with no audit trail and no way to keep client and internal boards linked.

The solution

I designed and built a Laravel web application on a service-layer architecture with dependency-injected TrelloService, MondayService, DataMapper, and AuditLogService components, driving Trello REST and Monday.com GraphQL APIs. It supports configurable status mapping, task-type synchronization, dual client–internal boards with item linking, fuzzy name matching for member assignment, and rich imports of descriptions, comments, and attachments — deployed to AWS with GitHub Actions CI/CD.

How it works

  • Service-layer architecture with dependency-injected Trello/Monday services
  • REST + GraphQL API orchestration with board-level caching
  • Configurable status mapping and task-type synchronization
  • Dual client–internal boards with item linking and fuzzy member matching
  • Rich imports: descriptions, comments, and attachments
  • Real-time migration progress, job history, and full audit logging
  • AWS deployment with GitHub Actions–based CI/CD

Results

  • 70+ client workspaces migrated successfully
  • Weeks of manual recreation replaced by monitored, auditable jobs
  • Client and internal boards stay linked after migration

Stack

Laravel PHP GraphQL REST APIs Monday.com Trello AWS GitHub Actions

AI · Workflow Orchestration

Meeting → Action-Items AI Pipeline

Flow diagram of the AI meeting pipeline: Fireflies.ai transcripts processed by Claude and OpenAI, delivered to Notion, Monday.com, Gmail, and Slack
20+
users incl. CXOs
Auto
owner assignment
0
manual triage steps

The problem

After every meeting, someone had to re-listen, write notes, extract action items, post them to the right project board, and chase owners. Across 20+ people and daily meetings, post-meeting admin consumed hours and items regularly slipped through.

The solution

I built and deployed an AI pipeline that ingests Fireflies.ai transcripts, uses Claude and OpenAI to generate notes, summaries, and action items, routes each action item to the correct Monday.com task board by meeting name, assigns it to the right owner, and delivers summaries via Notion, Gmail, and Slack.

How it works

  • Fireflies.ai transcript ingestion for every recorded meeting
  • LLM processing (Claude + OpenAI) for notes, summaries, and action items
  • Automatic board routing by meeting name
  • Owner detection and per-item assignment
  • Delivery to Notion, Monday.com, Gmail, and Slack

Results

  • Rolled out to 20+ internal users across teams and CXOs
  • Post-meeting admin and duplicate data entry sharply reduced
  • Action items land on the right board, assigned, before the room empties

Stack

n8n Fireflies.ai Claude OpenAI Notion Monday.com Gmail API Slack API

AI · Sales Automation

AI Follow-Up Agent for Lead Nurturing

Flow diagram of the AI follow-up agent connecting GoHighLevel leads to OpenAI-generated call, SMS, and email sequences via Twilio and ElevenLabs
3
channels: call · SMS · email
AI
voice + copy generation
24/7
always-on nurturing

The problem

Leads in GoHighLevel went cold because follow-up depended on humans remembering to call, text, and email — and generic drip campaigns ignored what each lead had actually done.

The solution

I developed an AI Follow-Up Agent using n8n that watches lead interactions in GoHighLevel and generates contextual follow-up with OpenAI — placing voice calls with ElevenLabs speech through Twilio, and sending personalized SMS and email sequences that adapt to each lead's behaviour.

How it works

  • Lead-interaction triggers from GoHighLevel
  • OpenAI-generated contextual messaging per lead
  • AI voice calls via Twilio + ElevenLabs
  • Multi-channel sequences: call, SMS, and email
  • Behaviour-based branching instead of fixed drips

Results

  • Every lead gets timely, personalized follow-up across three channels
  • Sales team freed from manual sequence management
  • Follow-up quality no longer depends on rep workload

Stack

n8n GoHighLevel OpenAI Twilio ElevenLabs

Automation · n8n

Monday.com Board Sync Suite

Diagram of n8n automations bi-directionally synchronizing Monday.com client, internal, project, and task boards with Slack alerting
2-way
status synchronization
6h
scheduled sync cadence
0
manual reconciliation

The problem

Client-facing and internal Monday.com boards drifted apart constantly: statuses updated on one side but not the other, renamed or deleted items left orphans, and project boards never reflected the true state of task boards.

The solution

I designed an end-to-end n8n automation suite on Monday.com webhooks: client update propagation with user mentions, bi-directional status synchronization via configurable mappings, dynamic item movement across groups, cascading renames and deletions for linked items, plus a second scalable automation aligning Project and Task boards with dynamic column/label management and scheduled syncs (daily and 6-hour intervals). Failures alert to Slack in real time.

How it works

  • Webhook-driven item creation, update, and deletion handling
  • Bi-directional status sync via configurable mappings
  • Cascading renames and deletions for linked items
  • Dynamic project column and status label management
  • Scheduled syncs (daily + 6-hour) for portfolio-to-task alignment
  • Real-time failure alerts to Slack

Results

  • Cross-board data consistency without manual reconciliation
  • Project health tracking reflects reality, on schedule
  • Failures surface in Slack immediately instead of silently drifting

Stack

n8n Monday.com Webhooks GraphQL Slack API

AI · Research Automation

STR Compliance Research Automation

Flow diagram of the short-term-rental compliance research automation using the Perplexity API to produce cited reports in Google Docs with Slack notifications
Min
per report, not hours
100%
source-cited output
Auto
Docs + Slack delivery

The problem

Researching short-term-rental (STR) compliance rules per jurisdiction meant hours of manual searching, reading, and report writing — repeated for every new market, with inconsistent quality and no citations.

The solution

I automated the whole workflow in n8n: the Perplexity API performs the research, results are structured into professional, source-cited reports written straight into Google Docs, and Slack notifies the team the moment a report is ready.

How it works

  • Perplexity API research with source citations preserved
  • Structured, professional report generation into Google Docs
  • Slack notifications on completion
  • Repeatable per-jurisdiction runs with consistent quality

Results

  • Manual research time reduced dramatically — hours to minutes
  • Every report is source-cited and consistently formatted
  • New jurisdictions covered on demand

Stack

n8n Perplexity API Google Docs API Slack API

Automation · Data Extraction

Spotify Playlist Curator Intelligence Tool

Diagram of the Python automation using Playwright and the Spotify API to scrape and verify playlist curator contacts
3,000+
verified curators
40h→min
weekly research time
↑
placement rates

The problem

A music-marketing team was manually hunting playlist curators — 40+ hours per week of searching, cross-checking, and copying contact data, and the pipeline of verified curators still ran dry.

The solution

I built a Python automation tool combining Playwright browser automation with the Spotify API to discover playlists, extract and verify curator information, and compile everything into a clean, deduplicated dataset ready for outreach.

How it works

  • Playwright-driven discovery across playlist ecosystems
  • Spotify API enrichment and verification of curator data
  • Deduplication and validation for outreach-ready records
  • Re-runnable pipeline to keep the dataset fresh

Results

  • 3,000+ verified playlist curators compiled
  • Manual research cut from 40+ hours per week to minutes
  • Outreach efficiency and playlist placement rates improved

Stack

Python Playwright Spotify API

RPA · Data Pipeline

Utility Bill Data Pipelines (PG&E + SFWater)

Robomotion workflow diagram of the PG&E and SFWater utility bill automation bots showing login, PDF download, OCR, and database steps
2
providers, one pipeline
100%
hands-off retrieval
OCR
PDF → database

The problem

The client needed billing data from PG&E and SFWater for a large set of accounts. Staff were logging in to two portals manually, downloading PDF bills one by one, re-typing values into a database, and filing documents — slow, error-prone, and impossible to scale.

The solution

I built unattended Robomotion bots for both providers: each logs in to its portal, iterates through every account from an Excel-driven config, downloads PDF bills, runs Tesseract OCR to extract billing values, validates and inserts data into PostgreSQL, and archives source PDFs to Google Drive and DigitalOcean Spaces. Discord notifications report every start, resume, and error, and both providers feed one shared schema for unified reporting.

How it works

  • Automated portal login and account iteration for two utility providers
  • PDF download and layout-aware OCR extraction with Tesseract
  • Field parsing, validation, and inserts into a shared PostgreSQL schema
  • Dual archival to Google Drive and DigitalOcean Spaces
  • Discord alerting with automatic resume after interruptions

Results

  • Bill retrieval and data entry became fully hands-off for both providers
  • One clean, queryable database across PG&E and SFWater
  • Errors surface in Discord within seconds instead of weeks later

Stack

Robomotion Tesseract OCR PostgreSQL Excel Google Drive API DigitalOcean Spaces Discord Webhooks

RPA · Property Management

Automated Bill Submission on AppFolio

Illustration of automated bill payment workflow for the AppFolio property management platform
Batch
bill after bill, unattended
0
missed attachments
Multi
property portfolios

The problem

Real-estate administrators were submitting vendor bills on AppFolio.com by hand: log in, open the bill form, type vendor and invoice details, attach files, save, repeat. Across multiple properties this consumed hours every week and invited data-entry mistakes.

The solution

I built a Robomotion bot (JavaScript) that logs in with admin credentials, navigates to bill entry, fills vendor and invoice fields, uploads invoice attachments, saves the bill, and immediately starts the next one — with error detection around each submission so a single failure never silently corrupts a batch.

How it works

  • Automatic login and navigation to the bill-entry workflow
  • Vendor, invoice, and amount fields filled from structured input
  • Automated file uploads for invoices and receipts
  • Per-bill error detection with safe continue/retry behaviour
  • Batch mode: submit bill after bill without interruption

Results

  • Bill entry across multiple property portfolios runs as a batch job
  • Attachment handling and field entry are consistent on every bill
  • Scales to any number of properties without extra headcount

Stack

Robomotion JavaScript AppFolio

Software · Industrial IoT

Villicus Industrial Monitoring Server

Architecture diagram of the Villicus monitoring system server connecting client devices to Micro800 PLCs over TCP/IP
C#→Py
legacy conversion
Real-time
PLC tag streaming
24/7
fault-tolerant uptime

The problem

An industrial automation client had a legacy C# TCP server bridging client devices and Micro800-series PLCs. It needed to move to Python while preserving robust communication with an existing PHP client — and industrial environments punish flaky networking and unhandled errors.

The solution

I converted the C# project to a multithreaded Python TCP server that maintains persistent connections, reads and writes PLC tag values, and streams tag updates in real time. JSON serialization plus zlib/base64 compression keeps bandwidth low; robust exception handling keeps the server alive through network faults; configuration is externalized for deployment across plant networks.

How it works

  • Full C# → Python conversion with a compatible PHP client protocol
  • Real-time TCP/IP communication with Micro800 PLCs
  • Read, write, and subscribe semantics for PLC tag values
  • JSON serialization with zlib + base64 compression
  • Multithreaded concurrent client handling with fault tolerance

Results

  • Operators monitor and control PLCs remotely and safely
  • The server handles many concurrent clients without degrading
  • Deployed as a practical, real-world industrial solution

Stack

Python TCP/IP Sockets Multithreading Micro800 PLC JSON zlib

Software · Healthcare

Clinic Management System

Interface concept of the clinic management system built with Laravel, Livewire, and Alpine.js
1
system replaces the tool sprawl
TALL
modern Laravel stack
E2E
operational coverage

The problem

A clinic was coordinating patients, appointments, and records across disconnected tools and paper processes — slow for staff and opaque for management.

The solution

I designed and implemented a comprehensive Clinic Management System using Laravel, Livewire, and Alpine.js — a reactive, server-driven interface without a heavy SPA framework, covering the clinic's operational workflows end to end with a user-friendly experience.

How it works

  • Full-stack TALL-adjacent architecture: Laravel + Livewire + Alpine.js
  • Reactive UI without SPA complexity
  • End-to-end operational workflows for clinic staff
  • Built for maintainability and future feature growth

Results

  • Clinic operations consolidated into one coherent system
  • Staff work in a fast, reactive interface instead of paper trails
  • Seamless functionality across the clinic's daily workflows

Stack

Laravel Livewire Alpine.js MySQL

Browser Extension · Scraping

E-commerce Data Extraction Extension

Screenshot of the e-commerce data extraction browser extension scraping product titles, prices, and images
JSON
clean structured output
Bulk
single & batch imports
Auto
pagination handling

The problem

A client needed complete product catalogs — titles, prices, descriptions, specs, images, categories, URLs — from e-commerce sites, imported into their own platform. Copy-pasting was hopeless, and dynamic HTML broke naive scrapers.

The solution

I built a Chrome extension that extracts product data directly from the live DOM, normalizes it into structured JSON, opens product pages in parallel tabs for concurrent scraping, walks pagination automatically, and POSTs the collected dataset to the client's endpoint — supporting single and bulk product imports with titles, descriptions, images, and categories.

How it works

  • DOM-based extraction of titles, prices, specs, images, and URLs
  • Single and bulk product import to the target platform
  • Parallel tab processing for concurrent page scraping
  • Automatic pagination handling across result pages
  • Throttled, asynchronous execution that stays stable at volume
  • Defensive checks that filter incomplete or malformed records

Results

  • Full product catalogs collected in hours instead of weeks
  • Data arrives clean and structured — no post-processing needed
  • Re-runnable at any time to keep the dataset current

Stack

JavaScript Chrome Extension APIs DOM REST

What I do

Services

From a single bot to an end-to-end AI automation platform — here is what I can take off your plate.

AI Agents & LLM Integrations

AI-driven pipelines built on OpenAI, Claude, and OpenRouter: meeting-to-action-items agents, AI follow-up sequences, document understanding, classification, and structured data extraction inside your workflows.

Workflow Automation (n8n · Make · Zapier)

End-to-end orchestration across your SaaS stack — Monday.com, Notion, Airtable, GoHighLevel, Slack, Gmail — with webhooks, bi-directional syncs, and real-time failure alerting.

RPA Development

Production-grade robots built with UiPath, Robomotion, and Playwright that log in, read documents, move data, and recover from errors — unattended, on a schedule, with alerting built in.

Web Scraping & Data Extraction

Reliable scrapers with Playwright, Selenium, and Apify plus PDF/OCR extraction — turning messy websites and documents into clean, structured data in your database or API.

Backend & Full-Stack Development

API-first systems with Laravel, FastAPI, and Vue/Nuxt — service-layer architecture, REST & GraphQL integrations, and applications built to be maintained, not just launched.

Cloud, DevOps & CI/CD

AWS, DigitalOcean, and Linode deployments with Docker, Nginx, and GitHub Actions/GitLab CI pipelines — containerized, secrets-managed, and shipped continuously.

Who I am

About

Engineer first, automator by obsession.

I'm Mehadi Hasan, AI Automation Lead at Get Levrg and a Senior Automation & Backend Systems Engineer based in Dhaka, Bangladesh. I hold an MSc in Computer Science & Engineering from Jahangirnagar University, and I've spent 8+ years building software — from Android backends and Laravel platforms to industrial TCP servers, and now multi-service AI pipelines integrating LLMs, SaaS platforms, and cloud infrastructure.

My work today is AI-driven workflow orchestration: n8n and Make.com automations, LLM agents built on OpenAI and Claude, RPA with UiPath, Robomotion, and Playwright, and API-first backend systems deployed with CI/CD. I also lead a team of 5 engineers — delegating, mentoring, and shipping on time. My engineering background is what makes my automations different: they're built like software, with error handling, observability, and architecture that survives contact with the real world.

  • AI Automation Lead at Get Levrg — leading a team of 5 engineers
  • MSc in Computer Science & Engineering (Jahangirnagar University)
  • 300+ clients served and 349 projects delivered as a freelancer
  • Open-source author — Laravel CRUD Generator & Laravel Pro Kit
Laravel CRUD Generator Laravel Pro Kit

AI & Automation

n8n Make.com Zapier UiPath Robomotion Playwright Selenium OpenAI API Claude API OpenRouter Prompt Engineering OCR Automation Apify BeautifulSoup

Languages & Frameworks

Python PHP JavaScript TypeScript Java SQL Go (learning) Laravel FastAPI Vue.js Nuxt.js Livewire Alpine.js WordPress

Data, Cloud & DevOps

PostgreSQL MySQL Redis SQLite Oracle DB AWS DigitalOcean Linode Docker Nginx GitHub Actions GitLab CI/CD Linux

SaaS & Business Platforms

Monday.com GoHighLevel Notion Airtable Trello Fireflies.ai Twilio ElevenLabs Slack API Google Workspace APIs

Track record

Experience & Education

  1. Aug 2025 — Present

    AI Automation Lead

    Get Levrg

    Leading a team of 5 engineers building AI-driven automation for client operations: the Trello → Monday.com migration platform (70+ workspaces), the meeting-to-action-items AI pipeline (20+ users incl. CXOs), and the Monday.com board-sync automation suite — working with cross-functional teams, PMs, and CSMs to define requirements and ship on time.

  2. Jun 2021 — Aug 2025

    Software Engineer

    Arizona Web Pro

    Built AI and automation systems for US clients: an AI follow-up agent (n8n, GHL, OpenAI, Twilio, ElevenLabs), enterprise meeting-documentation automation, STR compliance research with Perplexity, RPA bots for PG&E and SFWater, a Laravel/Livewire clinic management system, the Spotify curator intelligence tool, and Laravel backends for multiple Android apps.

  3. Jan 2019 — Dec 2019

    Software Engineer

    JMI Group BD

    Designed, built, and maintained the 'JMI Marketing Ltd — JML' Android app in Java; identified and fixed bottlenecks to keep performance, quality, and responsiveness high.

  4. Jun 2016 — Jan 2020

    Web & Android Developer

    Fiverr (Freelance)

    Served 300+ clients and completed 349 projects across PHP, Laravel, Android, and digital marketing — the foundation of a client-first, ship-it work ethic.

Education

  1. 2019 · CGPA 3.55/4.00

    MSc, Computer Science & Engineering

    Jahangirnagar University

  2. 2018 · CGPA 3.55/4.00

    BSc, Computer Science & Engineering

    Daffodil International University

Good to know

Frequently Asked Questions

Straight answers to the questions clients ask before working with me.

What kind of processes can you automate?

Anything a person does repeatedly on a computer: logging into portals, downloading and reading documents (including PDFs via OCR), moving data between spreadsheets, databases and web apps, syncing SaaS tools like Monday.com and Notion, filling forms, scraping websites, and sending notifications. If a process has rules, it can almost certainly be automated — and AI/LLM steps now cover many of the fuzzy parts that used to need a human, like summarizing meetings or extracting action items.

Which automation tools and platforms do you use?

For workflow orchestration: n8n, Make.com, and Zapier. For RPA: UiPath, Robomotion, and Playwright/Selenium. For AI: OpenAI, Claude, and OpenRouter APIs with careful prompt engineering. Around them I use Python, PHP/Laravel, and JavaScript for custom logic, PostgreSQL/MySQL/Redis for storage, and AWS/DigitalOcean with Docker and CI/CD for deployment. I choose the lightest tool that solves the problem — sometimes that is a 200-line Python script, not a platform license.

Can you add AI to an existing workflow?

Yes — that is most of my current work. Real examples: a pipeline that turns Fireflies.ai meeting transcripts into owner-assigned action items on Monday.com using Claude and OpenAI; an AI follow-up agent that generates contextual calls, SMS, and emails for leads; and automated source-cited research reports via the Perplexity API. I integrate AI as steps inside your existing automation rather than forcing a rebuild.

How does a project usually start?

With a free 15-minute audit call. You walk me through the manual process, I tell you honestly whether automation makes sense, roughly what it would involve, and what it would cost. If it is a fit, I follow up with a fixed-scope proposal — no obligation either way.

How do you make sure a bot keeps working after delivery?

Every system I ship includes error handling, automatic retry/resume behaviour, and real-time alerting (Slack, Discord, or email) so failures surface immediately instead of silently. Deployments are containerized with CI/CD so fixes ship in minutes, and I offer ongoing maintenance for when target websites change their layout or credentials rotate.

Do you work with international clients and time zones?

Yes — most of my clients are in the US and Europe. I am based in Dhaka, Bangladesh (GMT+6), keep generous overlap with US and EU working hours, and have worked remotely with international teams since 2016 — including 300+ clients as a freelancer.

Contact

Let's automate something

Tell me about the process that is eating your team's hours. I'll reply within 24 hours with an honest take on whether automation can fix it.