AHSAN SYSTEMS

AHSAN SYSTEMS

AI agents and automation systems for real business operations.

I build systems that handle lead follow-up, research, customer calls, approvals, internal knowledge, data processing, and the repetitive work your team should not be doing manually.

Built with n8n, AI models, APIs, databases, and custom code when needed.

Book a discovery callSee my work
Top Rated on Upwork100% Job Success33 jobs$8K+ earned

SELECTED WORK

Systems built around the work, not the tool.

Multi-agent research system

Research that runs every day without tying up the team

Built for a US real estate fund. Two AI agents collect grants, investors, and land opportunities, structure the findings, score each opportunity against the fund's criteria, and prepare outreach. The team gets one approval brief with the opportunities worth reviewing.

n8n · Claude · Airtable · APIs · Scraping

View project

AI sales automation

The CRM handles the follow-up instead of waiting on someone to remember it

Built with n8n and GoHighLevel to manage the lead journey from the first inbound message. The system classifies intent, qualifies leads, updates pipeline stages, triggers follow-ups, and brings cold leads back into the conversation.

n8n · GoHighLevel · OpenAI · APIs

View project

AI product approval system

Product checks every 30 minutes, with a person making the final call when needed

Built for a live marketplace with a constant flow of new listings. The system checks products for compliance issues, image quality, SEO, and listing problems. Each result is sent to approval, rejection, or manual review.

n8n · Claude · Supabase · Human review

View project

AI voice receptionist

Inbound calls handled without leaving customers waiting

Built for a home services business. The voice agent answers calls, understands what the customer needs, checks technician availability through an API, books the appointment into the CRM, and sends the team a structured call summary.

Voice AI · GoHighLevel · APIs · Scheduling

View project

RAG knowledge system

Answers based on company documents, with the source attached

Documents from Google Drive are processed, chunked, embedded, and stored in Supabase with pgvector. The assistant retrieves the relevant company information before answering and returns links to the source material.

RAG · Supabase · pgvector · Google Drive · LLMs

View project

2M+ record data pipeline

More than 2 million vehicle records scraped and parsed into PostgreSQL in a couple of days

The pipeline collected data at scale, parsed the records into a consistent structure, and stored the results in PostgreSQL within a couple of days.

Python · PostgreSQL · Scraping · Data pipelines

View project

ARCHITECTURE PHILOSOPHY

Built around how your business actually works

The best automation is not the one with the most AI in it. It is the one that fits your process and keeps the right people in control.

I use AI where judgment or unstructured information is involved, normal logic where the outcome should stay predictable, and custom code when off-the-shelf tools are not enough.

01 / AI where it helps
02 / Rules where they make sense
03 / Human approval where it matters
04 / Custom code when needed

WHAT I BUILD

Useful systems for repetitive operational work.

AI agents

Agents that can research, qualify leads, score opportunities, retrieve information, create drafts, call APIs, and pass decisions to a person when human review makes more sense.

Workflow automation

n8n and Make workflows for CRM operations, lead routing, approvals, reporting, outreach, document processing, internal operations, and API integrations.

Voice AI

Voice agents for inbound and outbound calls. They can answer questions, qualify leads, check live business data, book appointments, update your CRM, and transfer the conversation to a person.

RAG and internal AI

Knowledge assistants that answer from your documents, databases, and internal business data.

Data pipelines and custom integrations

Scraping, data processing, APIs, PostgreSQL, Supabase, Python, FastAPI, AWS, and custom backend work.

What clients say

“Extremely professional. Very quick. High-quality code. Ahsan has a profound understanding of what he does. Highly recommended!”

Upwork client

PROCESS

How a project works

01

We talk through the process

You show me what your team does today, which tools are involved, where the manual work happens, and what you want the system to handle.

02

I map the system

I decide what should use normal automation, what actually benefits from AI, where custom code is needed, and where a person should stay in control.

03

I build and test it

I connect the tools, write the missing integrations, test the full workflow, and make sure the pieces work together as one system.

04

You get the system and the documentation

I walk you through how it works, how to operate it, and what to do when something needs changing later.

Have something your team should not be doing manually?

Book a call and show me the process. We can look at what happens today, what is worth automating, and what the system should look like.

Book a discovery callPrefer email? contact@ahsan.systems