Sohag Gain
Sohag Gain
// ai automation engineer

I build systems
that never sleep.

AI agents and automation pipelines that qualify leads, answer customers, and move data — without manual follow-up.

Open to Remote / Hybrid · Full-Time & Part-Time · AI Automation roles
// automation.canvas live
100+
Automation projects
25+
Clients served
50+
Technologies
// core expertise

What I actually build

Four areas where automation moves the needle most.

AI Agents

AI Agents & Assistants

Multi-agent systems for email, calendar, support, and lead qualification — Claude, GPT-5, Gemini with real memory, not scripted chat.

Workflow

Workflow Automation

End-to-end systems in n8n, Make, and Zapier connecting CRMs, inboxes, and marketing tools — follow-up in seconds, not hours.

CRM

GoHighLevel & CRM

Pipelines, snapshots, white-label builds, and AI chatbots wired into the CRM your team already runs on.

RAG

RAG & Knowledge Base

Documents turned into a searchable, AI-answerable knowledge base with vector embeddings.

// interactive demo

Watch an AI agent work

Simplified simulation of my Gmail & Calendar Assistant — one goal in, the agent plans and executes.

agent · sohag-gain live simulation
Interactive portfolio simulation — not live production data
// user request

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

○Understanding the request
○Finding John in contactscontacts.lookup
○Checking calendar availabilitycalendar.freeBusy
○Selecting the best open slotreasoning.select
○Drafting the email to Johngmail.draft
○Sending the emailgmail.send
○Automation complete
// workflow

How the system moves

An n8n-style view — click a node to step through. Simple or Technical.

Trigger

A new lead arrives — form, webhook, or inbound message. The run starts here.

// knowledge

Turn documents into answers

Simplified view of my RAG pipeline — documents in, grounded answers out.

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

"What's your refund policy?"

○Searching the knowledge base
○Found 3 relevant chunks
○Generating a grounded answer
○Answer ready
// grounded answer with citations

"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."

docs/returns.md · §2.1 docs/faq.md · §4 kb/policies/return-policy
Powered by RAG — traced to source chunks
// architecture

How intelligent business systems connect

One pipeline shape — a request comes in, an AI agent reasons, automation executes, the result lands where 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 ways.

Beforemanual · hours
Lead fills out a form0 min
Sits in an inbox, unopened+2 h
Manually entered into CRM+4 h
Follow-up if remembered+1 d
Lead has gone cold
Afterautomated · seconds
Lead fills out a form0 s
AI qualifies instantly+3 s
CRM updated, stage set+5 s
SMS/email in 60 s+60 s
Appointment booked
// engineering maturity

AI alone isn't enough. Systems need guardrails.

Two things separate a real system from a demo — when to ask a human, and 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.

// stack

Technologies I use

Grouped by what they do in a real system. Hover for detail.

AI
Claude OpenAI Gemini
Automation
n8n Make Zapier
CRM
GoHighLevel HubSpot
Development
Python FastAPI PostgreSQL Docker APIs · Webhooks
AI Infrastructure
LangChain LangGraph Pinecone MCP · RAG
// skills

Hands-on skills, mapped to real projects.

Proven in production, working daily, or actively learning — filter to explore.

Currently learning — quieter row
CrewAIQdrantChromaDBLlamaIndexFlowiseLangflowGraphQLAzure BasicsGoogle Cloud BasicsWhatsApp AutomationAI Voice AgentsText-to-SpeechAI SaaS DevelopmentScaling
// verified credentials

Certified where it counts

◈Verified

GoHighLevel Specialist Certification

Automatable · May 2026

View certificate
◈Verified

AI Automation & AI Agents

Hablu Programmer · March 2026

View certificate

Web Design & Development

LEDP · 2020–2021

Foundation program — the API-integration base behind my automation work.

// personal brand

Behind the systems

Sohag Gain
Sohag Gain
// ai automation engineer · founder, ai smart galaxy

BSc in Computer Science & Engineering. I design the pipelines that qualify leads, answer customers, and close the loop — so teams stop copying and start shipping.

Dhaka · Remote (GMT+6) · sohag@sohaggain.com

About me View work
// featured work

Recent builds

Production systems and AI agents — full source on GitHub.

n8n · GPT-5 · Gmail/Calendar API

AI Gmail & Calendar Assistant

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

n8nWhisperTelegram
View project
n8n · Pinecone · OpenAI/Gemini

AI RAG Chatbot & Knowledge Base

Documents into Pinecone as embeddings, then grounded answers with memory-enabled semantic search.

RAGVector DBGoogle Drive
View project
GoHighLevel · Claude API · n8n

AI Chatbot for Lead Qualification

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

GoHighLevelClaude API
View project
// why hire me

What actually makes the difference

Not adjectives — here's what you're getting.

01

Business-first thinking

Start with the bottleneck, not the tool — so the system fixes what's slowing you down.

02

Real engineering foundation

BSc in CSE — APIs, data, and logic under the workflow, not just drag-and-drop.

03

AI where it helps

AI for judgment calls, deterministic automation for everything else.

04

End-to-end ownership

Discovery → design → build → test → handover. One owner, no handoff gaps.

Have an automation problem, or need an AI system built?

Remote, hybrid, freelance — let's figure out what actually needs automating.

sohag@sohaggain.com · Contact form

Hire Me Discuss a Project View My Work