Sohag Gain
Sohag Gain
// ai automation engineer

I build systems
that never sleep.

I design and ship AI agents and automation systems — n8n, Make.com, Zapier & GoHighLevel — that qualify leads, answer customers, and move data without a human touching it.

Open to Remote / Hybrid · Full-Time & Part-Time · AI Automation roles
// workflow.canvas live
trigger new_lead ai agent claude · gpt-5 action update_crm result < 60s
n8n Make.com Zapier GoHighLevel Claude API OpenAI API Google Gemini LangChain Pinecone / RAG Python
// core expertise

What I actually build

Four areas I keep coming back to — because they're where automation moves the needle most for a business.

AI Agents & Assistants

Multi-agent systems that handle email, calendar, support, and lead qualification — built on Claude, GPT-5, and Gemini, with real memory across turns, not scripted chat.

Workflow Automation

End-to-end systems in n8n, Make.com, and Zapier that connect CRMs, inboxes, and marketing tools — so leads get followed up in seconds, not hours.

GoHighLevel & CRM Systems

Agency-grade GHL builds — pipelines, snapshots, white-label setups, and AI chatbots wired directly into the CRM your team already runs on.

RAG & Knowledge Base Systems

Document and site content turned into a searchable, AI-answerable knowledge base using vector embeddings — for support bots that actually know your business.

// interactive demo

Watch an AI agent work

This is a simplified simulation of my real Gmail & Calendar Assistant — one goal in, the agent plans and executes the steps.

Interactive portfolio simulation — not live production data
// user request

"Find tomorrow's available meeting slots and email John."

Understanding the request
Finding John in contacts
Checking calendar availability
Selecting the best open slot
Drafting the email to John
Sending the email
Automation complete
// interactive demo

Turn documents into an AI knowledge system

This is a simplified simulation of my real RAG Chatbot & Knowledge Base project — documents in, grounded answers out.

Documents
Chunking
Embeddings
Vector DB
Interactive portfolio simulation — not live production data
// sample question

"What's your refund policy?"

Searching the knowledge base
Found 3 relevant document chunks
Generating a grounded answer
Answer ready
// grounded answer

"Refunds are available within 30 days of purchase, provided the item is unused and in its original packaging. Contact support with your order number to start a return."

Powered by RAG — answer traced back to source documents
// architecture

How intelligent business systems connect

Every system I build follows the same layered logic — a request comes in, an AI agent reasons over it, automation carries out the steps, and the result lands somewhere your team can see it.

Input

Something happens — a form fill, a message, a missed call.

A form submission, inbound message, missed call, or scheduled trigger fires a webhook, passing a structured payload into the pipeline.

AI Agent

AI reads the request and figures out what to do next.

Claude, GPT-5, or Gemini processes the payload — using function calling and structured outputs to classify, qualify, or decide the next action.

Automation Layer

The right steps happen automatically, in the right order.

n8n, Make.com, or Zapier orchestrates branching logic, retries, and routing across connected nodes.

APIs & Integrations

The AI talks to the other apps your business already uses.

REST APIs and webhooks pass authenticated requests between the AI layer and connected tools.

CRM

The record gets saved and moved to the right stage.

GoHighLevel or HubSpot's API updates the contact record, sets the pipeline stage, and triggers the next touchpoint.

Database

Information is stored so it can be found again later.

PostgreSQL or a vector store (Pinecone) persists structured data or embeddings for retrieval.

Business Outcome

The task gets done — no one had to do it by hand.

The pipeline resolves to a logged, auditable outcome — timestamped, with a status a human can check.

// the difference

Before automation, after automation

The same lead, handled two different ways.

Before
Lead fills out a form
Sits in an inbox, unopened
Manually entered into a CRM — hours later
Follow-up email sent, if remembered
Lead has gone cold
After
Lead fills out a form
AI agent qualifies it instantly
CRM updated, pipeline stage set automatically
SMS/email follow-up sent within 60 seconds
Rep gets an alert, appointment gets booked
// engineering maturity

AI alone isn't enough. Systems need guardrails.

Two things separate a real system from a demo — knowing when to ask a human, and knowing what to do when something breaks.

Human-in-the-loop

AI proposes. A human decides.

AI analyzes the situation
AI proposes an action
Flagged for human approval
Human approves — then it executes

For anything with real stakes — money, a customer message, a record change — the system pauses for a human instead of guessing.

Failure handling

When something breaks, it doesn't fail silently.

API call fails
Automatic retry (attempt 2)
Automatic retry (attempt 3)
Still failing — human gets an alert, with context

Good automation doesn't only handle the happy path. It knows what to do — and who to tell — when something goes wrong.

// verified credentials
GoHighLevel Specialist
Automatable · May 2026
AI Automation & AI Agents
Hablu Programmer · March 2026
View all credentials
// featured work

Recent builds

A sample of production automation systems and AI agents — full portfolio and source available on GitHub.

n8n · GPT-5 · Gmail/Calendar API

AI Gmail & Calendar Assistant

Multi-agent assistant that handles email and calendar actions from text or voice, with contact lookup and memory.

n8nWhisperTelegram
View project
n8n · Pinecone · OpenAI/Gemini

AI RAG Chatbot & Knowledge Base

Syncs documents into Pinecone as embeddings, then answers questions with memory-enabled semantic search.

RAGVector DBGoogle Drive
View project
GoHighLevel · Claude API · n8n

AI Chatbot for Lead Qualification

Answers service questions, qualifies leads, and detects booking intent — with human handoff for edge cases.

GoHighLevelClaude API
View project
// why hire me

What actually makes the difference

Not a list of adjectives — here's what you're actually getting.

01

Business-first thinking

I start with the operational bottleneck, not the tool — so the system I build actually fixes what's slowing you down, not just something automatable.

02

Real engineering foundation

A BSc in Computer Science & Engineering behind the automation work — I understand APIs, data, and logic, not just how to drag nodes in a no-code builder.

03

AI where it actually helps

I combine AI agents with deterministic workflow automation — using AI for judgment calls, and plain automation for everything that doesn't need it.

04

End-to-end ownership

Discovery, design, build, test, and handover — I can take a process from "this is broken" to "this runs itself" without handing it off midway.

Have a role — or an automation problem?

I'm open to remote/hybrid roles, and to automation projects for agencies and founders.

Contact Me Download Resume